feat: apply local modifications to WhisperLive-Server
This commit is contained in:
parent
05648af633
commit
83edfff9d3
@ -1,51 +0,0 @@
|
||||
FROM python:3.10-bookworm
|
||||
|
||||
ARG DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
# Create log directories with proper permissions
|
||||
RUN mkdir -p /app/logs && \
|
||||
touch /app/logs/whisperlive.log && \
|
||||
touch /app/logs/connections.log && \
|
||||
chmod 666 /app/logs/whisperlive.log && \
|
||||
chmod 666 /app/logs/connections.log
|
||||
|
||||
# install lib required for pyaudio
|
||||
RUN apt update && apt install -y portaudio19-dev && apt-get clean && rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# update pip to support for whl.metadata -> less downloading
|
||||
RUN pip install --no-cache-dir -U "pip>=24"
|
||||
|
||||
# create a working directory
|
||||
WORKDIR /app
|
||||
|
||||
# install the requirements for running the whisper-live server
|
||||
COPY requirements/server.txt /app/
|
||||
RUN pip install -r server.txt && rm server.txt
|
||||
|
||||
COPY whisper_live /app/whisper_live
|
||||
COPY run_server.py /app
|
||||
|
||||
# Port options
|
||||
EXPOSE ${PORT_WHISPERLIVE}
|
||||
EXPOSE ${PORT_WHISPERLIVE_SSL}
|
||||
ARG PORT_WHISPERLIVE
|
||||
ENV PORT_WHISPERLIVE=${PORT_WHISPERLIVE}
|
||||
ARG PORT_WHISPERLIVE_SSL
|
||||
ENV PORT_WHISPERLIVE_SSL=${PORT_WHISPERLIVE_SSL}
|
||||
|
||||
# SSL options
|
||||
ARG WHISPERLIVE_SSL
|
||||
ENV WHISPERLIVE_SSL=${WHISPERLIVE_SSL}
|
||||
|
||||
# Model options
|
||||
ARG WHISPL_USE_CUSTOM_MODEL
|
||||
ENV WHISPL_USE_CUSTOM_MODEL=${WHISPL_USE_CUSTOM_MODEL}
|
||||
ARG FASTERWHISPER_MODEL
|
||||
ENV FASTERWHISPER_MODEL=${FASTERWHISPER_MODEL}
|
||||
|
||||
CMD ["sh", "-c", "\
|
||||
if [ \"$WHISPERLIVE_SSL\" = \"true\" ]; then \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE_SSL --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL --ssl_cert_path /app/ssl; \
|
||||
else \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL --no_single_model; \
|
||||
fi"]
|
||||
@ -1,45 +0,0 @@
|
||||
FROM python:3.10-bookworm
|
||||
|
||||
ARG DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
# Create log directories with proper permissions
|
||||
RUN mkdir -p /app/logs && \
|
||||
touch /app/logs/whisperlive.log && \
|
||||
touch /app/logs/connections.log && \
|
||||
chmod 666 /app/logs/whisperlive.log && \
|
||||
chmod 666 /app/logs/connections.log
|
||||
|
||||
# install lib required for pyaudio
|
||||
RUN apt update && apt install -y portaudio19-dev && apt-get clean && rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# update pip to support for whl.metadata -> less downloading
|
||||
RUN pip install --no-cache-dir -U "pip>=24"
|
||||
|
||||
# create a working directory
|
||||
WORKDIR /app
|
||||
|
||||
# install the requirements for running the whisper-live server
|
||||
COPY requirements/server.txt /app/
|
||||
RUN pip install -r server.txt && rm server.txt
|
||||
|
||||
COPY whisper_live /app/whisper_live
|
||||
COPY run_server.py /app
|
||||
|
||||
# Copy application files
|
||||
EXPOSE ${PORT_WHISPERLIVE}
|
||||
EXPOSE ${PORT_WHISPERLIVE_SSL}
|
||||
ARG PORT_WHISPERLIVE
|
||||
ENV PORT_WHISPERLIVE=${PORT_WHISPERLIVE}
|
||||
ARG PORT_WHISPERLIVE_SSL
|
||||
ENV PORT_WHISPERLIVE_SSL=${PORT_WHISPERLIVE_SSL}
|
||||
ARG FASTERWHISPER_MODEL
|
||||
ENV FASTERWHISPER_MODEL=${FASTERWHISPER_MODEL}
|
||||
ARG WHISPERLIVE_SSL
|
||||
ENV WHISPERLIVE_SSL=${WHISPERLIVE_SSL}
|
||||
|
||||
CMD ["sh", "-c", "\
|
||||
if [ \"$WHISPERLIVE_SSL\" = \"true\" ]; then \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE_SSL --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL --ssl_cert_path /app/ssl; \
|
||||
else \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL; \
|
||||
fi"]
|
||||
@ -1,49 +0,0 @@
|
||||
FROM python:3.10-bookworm
|
||||
|
||||
ARG DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
# Create log directories with proper permissions
|
||||
RUN mkdir -p /app/logs && \
|
||||
touch /app/logs/whisperlive.log && \
|
||||
touch /app/logs/connections.log && \
|
||||
chmod 666 /app/logs/whisperlive.log && \
|
||||
chmod 666 /app/logs/connections.log
|
||||
|
||||
# install lib required for pyaudio
|
||||
RUN apt update && apt install -y portaudio19-dev && apt-get clean && rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# update pip to support for whl.metadata -> less downloading
|
||||
RUN pip install --no-cache-dir -U "pip>=24"
|
||||
|
||||
# create a working directory
|
||||
WORKDIR /app
|
||||
|
||||
# install the requirements for running the whisper-live server
|
||||
COPY requirements/server.txt /app/
|
||||
RUN pip install -r server.txt && rm server.txt
|
||||
|
||||
# make the paths of the nvidia libs installed as wheels visible. equivalent to:
|
||||
# export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
|
||||
ENV LD_LIBRARY_PATH="/usr/local/lib/python3.10/site-packages/nvidia/cublas/lib:/usr/local/lib/python3.10/site-packages/nvidia/cudnn/lib"
|
||||
|
||||
COPY whisper_live /app/whisper_live
|
||||
COPY run_server.py /app
|
||||
|
||||
# Copy application files
|
||||
EXPOSE ${PORT_WHISPERLIVE}
|
||||
EXPOSE ${PORT_WHISPERLIVE_SSL}
|
||||
ARG PORT_WHISPERLIVE
|
||||
ENV PORT_WHISPERLIVE=${PORT_WHISPERLIVE}
|
||||
ARG PORT_WHISPERLIVE_SSL
|
||||
ENV PORT_WHISPERLIVE_SSL=${PORT_WHISPERLIVE_SSL}
|
||||
ARG FASTERWHISPER_MODEL
|
||||
ENV FASTERWHISPER_MODEL=${FASTERWHISPER_MODEL}
|
||||
ARG WHISPERLIVE_SSL
|
||||
ENV WHISPERLIVE_SSL=${WHISPERLIVE_SSL}
|
||||
|
||||
CMD ["sh", "-c", "\
|
||||
if [ \"$WHISPERLIVE_SSL\" = \"true\" ]; then \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE_SSL --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL --ssl_cert_path /app/ssl; \
|
||||
else \
|
||||
python3 -u run_server.py --port $PORT_WHISPERLIVE --backend faster_whisper --faster_whisper_custom_model_path /app/models/$FASTERWHISPER_MODEL; \
|
||||
fi"]
|
||||
File diff suppressed because it is too large
Load Diff
5
.env
5
.env
@ -1,9 +1,10 @@
|
||||
# Whisper live settings
|
||||
APP_WS_PROTOCOL=wss
|
||||
APP_URL=kevlarai.com
|
||||
APP_URL=classroomcopilot.ai
|
||||
|
||||
PORT_WHISPERLIVE=5050
|
||||
PORT_WHISPERLIVE=5000
|
||||
PORT_WHISPERLIVE_SSL=5053
|
||||
HTTP_PORT=8080
|
||||
WHISPERLIVE_SSL=false
|
||||
|
||||
WHISPL_USE_CUSTOM_MODEL=false
|
||||
|
||||
20
Dockerfile
20
Dockerfile
@ -20,22 +20,24 @@ WORKDIR /app
|
||||
|
||||
# install the requirements for running the whisper-live server
|
||||
COPY requirements/server.txt /app/
|
||||
RUN pip install -r server.txt && rm server.txt
|
||||
RUN pip install --no-cache-dir "setuptools<70.0.0" wheel
|
||||
RUN pip install -r server.txt
|
||||
RUN pip install --no-build-isolation openai-whisper==20240930
|
||||
RUN rm server.txt
|
||||
|
||||
# make the paths of the nvidia libs installed as wheels visible
|
||||
ENV LD_LIBRARY_PATH="/usr/local/lib/python3.10/site-packages/nvidia/cublas/lib:/usr/local/lib/python3.10/site-packages/nvidia/cudnn/lib"
|
||||
RUN pip install --no-cache-dir nvidia-cublas-cu12 nvidia-cudnn-cu12
|
||||
ENV LD_LIBRARY_PATH="/usr/local/lib/python3.10/site-packages/nvidia/cublas/lib:/usr/local/lib/python3.10/site-packages/nvidia/cudnn/lib:/usr/local/lib/python3.10/site-packages/torch/lib:${LD_LIBRARY_PATH}"
|
||||
|
||||
COPY whisper_live /app/whisper_live
|
||||
COPY run_server.py /app
|
||||
COPY hybrid_server.py /app
|
||||
|
||||
# Copy application files
|
||||
EXPOSE ${PORT_WHISPERLIVE}
|
||||
ARG PORT_WHISPERLIVE
|
||||
ENV PORT_WHISPERLIVE=${PORT_WHISPERLIVE}
|
||||
ARG FASTERWHISPER_MODEL
|
||||
ENV FASTERWHISPER_MODEL=${FASTERWHISPER_MODEL}
|
||||
# Expose both WebSocket and HTTP ports
|
||||
EXPOSE 5000 8080
|
||||
|
||||
CMD ["python3", "-u", "run_server.py", "--port", "${PORT_WHISPERLIVE}", "--backend", "faster_whisper"]
|
||||
# Use the hybrid server by default
|
||||
CMD python3 -u hybrid_server.py --websocket-port 5000 --http-port 8080 --backend faster_whisper
|
||||
|
||||
# CMD ["python3", "-u", "run_server.py", "--port", "${PORT_WHISPERLIVE}", "--backend", "faster_whisper", "--faster_whisper_custom_model_path", "/app/models/${FASTERWHISPER_MODEL}", "--ssl_cert_path", "/app/ssl"]
|
||||
|
||||
|
||||
260
HYBRID_SERVER_README.md
Normal file
260
HYBRID_SERVER_README.md
Normal file
@ -0,0 +1,260 @@
|
||||
# WhisperLive Hybrid Server
|
||||
|
||||
This hybrid server extends the original WhisperLive-Server to support both WebSocket connections (for real-time audio streaming) and HTTP endpoints (for file transcription) in a single container.
|
||||
|
||||
## Features
|
||||
|
||||
- **WebSocket Server**: Original real-time audio transcription functionality
|
||||
- **HTTP Server**: New file upload and transcription endpoints
|
||||
- **Single Container**: Both services run in the same Docker container
|
||||
- **GPU Sharing**: Both services share the same GPU resources
|
||||
|
||||
## Architecture
|
||||
|
||||
The hybrid server runs two services simultaneously:
|
||||
1. **WebSocket Server**: Handles real-time audio streaming transcription
|
||||
2. **HTTP Server**: Handles file uploads and transcription requests
|
||||
|
||||
Both services use the same WhisperLive transcriber instance, ensuring efficient resource usage.
|
||||
|
||||
## Ports
|
||||
|
||||
- **WebSocket Port**: Default 5050 (configurable via `PORT_WHISPERLIVE`)
|
||||
- **HTTP Port**: Default 8080 (configurable via `HTTP_PORT`)
|
||||
|
||||
## HTTP Endpoints
|
||||
|
||||
### 1. Health Check
|
||||
```
|
||||
GET /health
|
||||
```
|
||||
Returns server health status.
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"status": "healthy",
|
||||
"service": "WhisperLive Hybrid Server"
|
||||
}
|
||||
```
|
||||
|
||||
### 2. OpenAI Compatible Endpoints
|
||||
```
|
||||
POST /v1/audio/transcriptions
|
||||
POST /v1/audio/translations
|
||||
```
|
||||
Fully compatible drop-in replacements for the standard OpenAI Whisper API.
|
||||
|
||||
**Parameters:**
|
||||
- `file` (required): Audio file (WAV, MP3, FLAC, M4A, OGG, WEBM, MP4, MPEG, MPGA)
|
||||
- `model` (optional): Model size (default: "base")
|
||||
- `language` (optional): Language code (e.g., "en", "es", "fr")
|
||||
- `prompt` (optional): Text to guide the model's style
|
||||
- `response_format` (optional): "json", "text", "srt", "verbose_json", "vtt" (default: "json")
|
||||
- `temperature` (optional): Sampling temperature (0.0 to 1.0)
|
||||
|
||||
**Example Request:**
|
||||
```bash
|
||||
curl -X POST http://localhost:8080/v1/audio/transcriptions \
|
||||
-H "Content-Type: multipart/form-data" \
|
||||
-F "file=@audio.wav" \
|
||||
-F "model=whisper-1" \
|
||||
-F "response_format=json"
|
||||
```
|
||||
|
||||
**Response (JSON format):**
|
||||
```json
|
||||
{
|
||||
"text": "Hello, this is a test."
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Legacy File Transcription
|
||||
```
|
||||
POST /transcribe
|
||||
```
|
||||
Transcribes an uploaded audio file.
|
||||
|
||||
**Parameters:**
|
||||
- `file` (required): Audio file (WAV, MP3, FLAC, M4A, OGG, WEBM)
|
||||
- `language` (optional): Language code (e.g., "en", "es", "fr")
|
||||
- `task` (optional): "transcribe" or "translate" (default: "transcribe")
|
||||
- `model` (optional): Model size (default: "base")
|
||||
|
||||
**Example Request:**
|
||||
```bash
|
||||
curl -X POST http://localhost:8080/transcribe \
|
||||
-F "file=@audio.wav" \
|
||||
-F "language=en" \
|
||||
-F "task=transcribe" \
|
||||
-F "model=base"
|
||||
```
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"segments": [
|
||||
{
|
||||
"start": 0.0,
|
||||
"end": 2.5,
|
||||
"text": "Hello, this is a test.",
|
||||
"no_speech_prob": 0.1
|
||||
}
|
||||
],
|
||||
"info": {
|
||||
"language": "en",
|
||||
"language_probability": 0.95,
|
||||
"duration": 10.5,
|
||||
"duration_after_vad": 10.5,
|
||||
"transcription_options": {}
|
||||
},
|
||||
"filename": "audio.wav"
|
||||
}
|
||||
```
|
||||
|
||||
### 3. URL Transcription (Placeholder)
|
||||
```
|
||||
POST /transcribe/url
|
||||
```
|
||||
Endpoint for transcribing audio from URLs (ready for implementation).
|
||||
|
||||
## Usage Examples
|
||||
|
||||
### Python Client
|
||||
```python
|
||||
import requests
|
||||
|
||||
# Transcribe a file
|
||||
with open('audio.wav', 'rb') as f:
|
||||
response = requests.post('http://localhost:8080/transcribe',
|
||||
files={'file': f},
|
||||
data={'language': 'en', 'model': 'base'})
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
print(f"Transcription: {result['segments']}")
|
||||
```
|
||||
|
||||
### JavaScript/Node.js
|
||||
```javascript
|
||||
const FormData = require('form-data');
|
||||
const fs = require('fs');
|
||||
|
||||
const form = new FormData();
|
||||
form.append('file', fs.createReadStream('audio.wav'));
|
||||
form.append('language', 'en');
|
||||
form.append('model', 'base');
|
||||
|
||||
fetch('http://localhost:8080/transcribe', {
|
||||
method: 'POST',
|
||||
body: form
|
||||
})
|
||||
.then(response => response.json())
|
||||
.then(result => console.log(result));
|
||||
```
|
||||
|
||||
### cURL
|
||||
```bash
|
||||
# Basic transcription
|
||||
curl -X POST http://localhost:8080/transcribe \
|
||||
-F "file=@audio.wav"
|
||||
|
||||
# With parameters
|
||||
curl -X POST http://localhost:8080/transcribe \
|
||||
-F "file=@audio.wav" \
|
||||
-F "language=es" \
|
||||
-F "task=translate" \
|
||||
-F "model=small"
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
### Environment Variables
|
||||
- `PORT_WHISPERLIVE`: WebSocket port (default: 5050)
|
||||
- `HTTP_PORT`: HTTP port (default: 8080)
|
||||
- `FASTERWHISPER_MODEL`: Custom model path
|
||||
- `OMP_NUM_THREADS`: OpenMP thread count
|
||||
|
||||
### Docker Compose
|
||||
```yaml
|
||||
services:
|
||||
whisperlive:
|
||||
ports:
|
||||
- "5050:5050" # WebSocket
|
||||
- "8080:8080" # HTTP
|
||||
environment:
|
||||
PORT_WHISPERLIVE: 5050
|
||||
HTTP_PORT: 8080
|
||||
```
|
||||
|
||||
## Testing
|
||||
|
||||
### 1. Test Script
|
||||
Run the Python test script:
|
||||
```bash
|
||||
python3 test_http_endpoints.py
|
||||
```
|
||||
|
||||
### 2. Web Interface
|
||||
Open `test_form.html` in a web browser to test the HTTP endpoints with a user-friendly interface.
|
||||
|
||||
### 3. Health Check
|
||||
```bash
|
||||
curl http://localhost:8080/health
|
||||
```
|
||||
|
||||
## Backend Support
|
||||
|
||||
Currently, the HTTP endpoints support:
|
||||
- **faster_whisper**: Full support for all features
|
||||
- **tensorrt**: Basic support (needs adaptation)
|
||||
- **openvino**: Basic support (needs adaptation)
|
||||
|
||||
## File Size Limits
|
||||
|
||||
- Maximum file size: 100MB
|
||||
- Supported formats: WAV, MP3, FLAC, M4A, OGG, WEBM
|
||||
|
||||
## Performance Considerations
|
||||
|
||||
- File transcription uses the same model instance as WebSocket connections
|
||||
- Temporary files are automatically cleaned up after processing
|
||||
- Both services share GPU memory efficiently
|
||||
- HTTP requests are processed in separate threads
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
1. **Port Already in Use**
|
||||
- Check if ports 5050 or 8080 are available
|
||||
- Use different ports via environment variables
|
||||
|
||||
2. **File Upload Errors**
|
||||
- Ensure file size is under 100MB
|
||||
- Check file format is supported
|
||||
- Verify file is not corrupted
|
||||
|
||||
3. **GPU Memory Issues**
|
||||
- Monitor GPU memory usage
|
||||
- Consider using smaller model sizes
|
||||
- Restart container if needed
|
||||
|
||||
### Logs
|
||||
Check container logs for detailed error information:
|
||||
```bash
|
||||
docker logs whisperlive
|
||||
```
|
||||
|
||||
## Migration from Original Server
|
||||
|
||||
The hybrid server is fully backward compatible. Your existing WebSocket clients will continue to work without changes. The HTTP endpoints are additional functionality that doesn't interfere with the original service.
|
||||
|
||||
## Future Enhancements
|
||||
|
||||
- [ ] Support for more audio formats
|
||||
- [ ] Batch file processing
|
||||
- [ ] Progress tracking for long files
|
||||
- [ ] Authentication and rate limiting
|
||||
- [ ] WebSocket support for file transcription progress
|
||||
BIN
__pycache__/hybrid_server.cpython-314.pyc
Normal file
BIN
__pycache__/hybrid_server.cpython-314.pyc
Normal file
Binary file not shown.
270
batch_transcribe.py
Normal file
270
batch_transcribe.py
Normal file
@ -0,0 +1,270 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Batch Transcription Script for WhisperLive
|
||||
Processes all audio files in a folder using the HTTP transcription endpoint
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
import time
|
||||
import argparse
|
||||
import requests
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Optional
|
||||
import logging
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class BatchTranscriber:
|
||||
def __init__(self, server_url: str = "http://localhost:8080"):
|
||||
self.server_url = server_url
|
||||
self.supported_formats = {'.wav', '.mp3', '.flac', '.m4a', '.ogg', '.webm'}
|
||||
|
||||
def get_audio_files(self, folder_path: str) -> List[Path]:
|
||||
"""Get all audio files from the specified folder"""
|
||||
folder = Path(folder_path)
|
||||
if not folder.exists():
|
||||
raise FileNotFoundError(f"Folder not found: {folder_path}")
|
||||
|
||||
audio_files = []
|
||||
for file_path in folder.iterdir():
|
||||
if file_path.is_file() and file_path.suffix.lower() in self.supported_formats:
|
||||
audio_files.append(file_path)
|
||||
|
||||
return sorted(audio_files)
|
||||
|
||||
def transcribe_file(self, file_path: Path, language: Optional[str] = None,
|
||||
task: str = "transcribe", model: str = "base") -> Dict:
|
||||
"""Transcribe a single audio file"""
|
||||
try:
|
||||
logger.info(f"Transcribing: {file_path.name}")
|
||||
|
||||
with open(file_path, 'rb') as f:
|
||||
files = {'file': f}
|
||||
data = {
|
||||
'language': language,
|
||||
'task': task,
|
||||
'model': model
|
||||
}
|
||||
|
||||
response = requests.post(f"{self.server_url}/transcribe",
|
||||
files=files, data=data, timeout=300)
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
logger.info(f"✅ Successfully transcribed: {file_path.name}")
|
||||
return result
|
||||
else:
|
||||
error_msg = response.text
|
||||
logger.error(f"❌ Failed to transcribe {file_path.name}: {error_msg}")
|
||||
return {'error': error_msg, 'status_code': response.status_code}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Error transcribing {file_path.name}: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def save_transcript(self, transcript_data: Dict, output_path: Path,
|
||||
format_type: str = "txt") -> bool:
|
||||
"""Save transcript in specified format"""
|
||||
try:
|
||||
if 'error' in transcript_data:
|
||||
return False
|
||||
|
||||
if format_type == "txt":
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
f.write(f"Transcription of: {transcript_data.get('filename', 'Unknown')}\n")
|
||||
f.write(f"Language: {transcript_data['info'].get('language', 'Auto-detected')}\n")
|
||||
f.write(f"Duration: {transcript_data['info'].get('duration', 0):.2f} seconds\n")
|
||||
f.write("=" * 50 + "\n\n")
|
||||
|
||||
for segment in transcript_data['segments']:
|
||||
f.write(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}\n")
|
||||
|
||||
elif format_type == "json":
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(transcript_data, f, indent=2, ensure_ascii=False)
|
||||
|
||||
elif format_type == "srt":
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
for i, segment in enumerate(transcript_data['segments'], 1):
|
||||
start_time = self.format_srt_time(segment['start'])
|
||||
end_time = self.format_srt_time(segment['end'])
|
||||
f.write(f"{i}\n{start_time} --> {end_time}\n{segment['text']}\n\n")
|
||||
|
||||
elif format_type == "vtt":
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
f.write("WEBVTT\n\n")
|
||||
for segment in transcript_data['segments']:
|
||||
start_time = self.format_vtt_time(segment['start'])
|
||||
end_time = self.format_vtt_time(segment['end'])
|
||||
f.write(f"{start_time} --> {end_time}\n{segment['text']}\n\n")
|
||||
|
||||
logger.info(f"💾 Saved transcript: {output_path}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Error saving transcript {output_path}: {str(e)}")
|
||||
return False
|
||||
|
||||
def format_srt_time(self, seconds: float) -> str:
|
||||
"""Format time for SRT subtitles"""
|
||||
hours = int(seconds // 3600)
|
||||
minutes = int((seconds % 3600) // 60)
|
||||
secs = int(seconds % 60)
|
||||
millisecs = int((seconds % 1) * 1000)
|
||||
return f"{hours:02d}:{minutes:02d}:{secs:02d},{millisecs:03d}"
|
||||
|
||||
def format_vtt_time(self, seconds: float) -> str:
|
||||
"""Format time for VTT subtitles"""
|
||||
hours = int(seconds // 3600)
|
||||
minutes = int((seconds % 3600) // 60)
|
||||
secs = int(seconds % 60)
|
||||
millisecs = int((seconds % 1) * 1000)
|
||||
return f"{hours:02d}:{minutes:02d}:{secs:02d}.{millisecs:03d}"
|
||||
|
||||
def batch_transcribe(self, input_folder: str, output_folder: str,
|
||||
language: Optional[str] = None, task: str = "transcribe",
|
||||
model: str = "base", format_type: str = "txt",
|
||||
delay: float = 1.0) -> Dict:
|
||||
"""Process all audio files in the input folder"""
|
||||
|
||||
# Create output folder if it doesn't exist
|
||||
output_path = Path(output_folder)
|
||||
output_path.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Get all audio files
|
||||
audio_files = self.get_audio_files(input_folder)
|
||||
if not audio_files:
|
||||
logger.warning(f"No audio files found in: {input_folder}")
|
||||
return {'processed': 0, 'successful': 0, 'failed': 0}
|
||||
|
||||
logger.info(f"Found {len(audio_files)} audio files to process")
|
||||
|
||||
results = {
|
||||
'processed': len(audio_files),
|
||||
'successful': 0,
|
||||
'failed': 0,
|
||||
'files': []
|
||||
}
|
||||
|
||||
for i, audio_file in enumerate(audio_files, 1):
|
||||
logger.info(f"Processing {i}/{len(audio_files)}: {audio_file.name}")
|
||||
|
||||
# Transcribe the file
|
||||
transcript_data = self.transcribe_file(audio_file, language, task, model)
|
||||
|
||||
if 'error' not in transcript_data:
|
||||
# Create output filename
|
||||
base_name = audio_file.stem
|
||||
output_file = output_path / f"{base_name}.{format_type}"
|
||||
|
||||
# Save transcript
|
||||
if self.save_transcript(transcript_data, output_file, format_type):
|
||||
results['successful'] += 1
|
||||
results['files'].append({
|
||||
'input': str(audio_file),
|
||||
'output': str(output_file),
|
||||
'status': 'success'
|
||||
})
|
||||
else:
|
||||
results['failed'] += 1
|
||||
results['files'].append({
|
||||
'input': str(audio_file),
|
||||
'output': str(output_file),
|
||||
'status': 'failed'
|
||||
})
|
||||
else:
|
||||
results['failed'] += 1
|
||||
results['files'].append({
|
||||
'input': str(audio_file),
|
||||
'output': None,
|
||||
'status': 'failed',
|
||||
'error': transcript_data.get('error', 'Unknown error')
|
||||
})
|
||||
|
||||
# Add delay between requests to avoid overwhelming the server
|
||||
if i < len(audio_files):
|
||||
time.sleep(delay)
|
||||
|
||||
return results
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='Batch transcribe audio files using WhisperLive')
|
||||
parser.add_argument('input_folder', help='Folder containing audio files')
|
||||
parser.add_argument('output_folder', help='Folder to save transcripts')
|
||||
parser.add_argument('--server', '-s', default='http://localhost:8080',
|
||||
help='WhisperLive server URL (default: http://localhost:8080)')
|
||||
parser.add_argument('--language', '-l', help='Language code (e.g., en, es, fr)')
|
||||
parser.add_argument('--task', '-t', choices=['transcribe', 'translate'], default='transcribe',
|
||||
help='Task to perform (default: transcribe)')
|
||||
parser.add_argument('--model', '-m', default='base',
|
||||
help='Model size (default: base)')
|
||||
parser.add_argument('--format', '-f', choices=['txt', 'json', 'srt', 'vtt'], default='txt',
|
||||
help='Output format (default: txt)')
|
||||
parser.add_argument('--delay', '-d', type=float, default=1.0,
|
||||
help='Delay between requests in seconds (default: 1.0)')
|
||||
parser.add_argument('--verbose', '-v', action='store_true',
|
||||
help='Verbose output')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.verbose:
|
||||
logging.getLogger().setLevel(logging.DEBUG)
|
||||
|
||||
try:
|
||||
# Initialize transcriber
|
||||
transcriber = BatchTranscriber(args.server)
|
||||
|
||||
# Check server health
|
||||
try:
|
||||
response = requests.get(f"{args.server}/health", timeout=5)
|
||||
if response.status_code != 200:
|
||||
logger.error(f"Server health check failed: {response.status_code}")
|
||||
sys.exit(1)
|
||||
logger.info("✅ Server health check passed")
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.error(f"❌ Cannot connect to server: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
# Process files
|
||||
results = transcriber.batch_transcribe(
|
||||
input_folder=args.input_folder,
|
||||
output_folder=args.output_folder,
|
||||
language=args.language,
|
||||
task=args.task,
|
||||
model=args.model,
|
||||
format_type=args.format,
|
||||
delay=args.delay
|
||||
)
|
||||
|
||||
# Print summary
|
||||
logger.info("\n" + "=" * 50)
|
||||
logger.info("BATCH TRANSCRIPTION COMPLETED")
|
||||
logger.info("=" * 50)
|
||||
logger.info(f"Total files processed: {results['processed']}")
|
||||
logger.info(f"Successful: {results['successful']}")
|
||||
logger.info(f"Failed: {results['failed']}")
|
||||
logger.info(f"Output folder: {args.output_folder}")
|
||||
logger.info(f"Output format: {args.format}")
|
||||
|
||||
if results['failed'] > 0:
|
||||
logger.warning("\nFailed files:")
|
||||
for file_info in results['files']:
|
||||
if file_info['status'] == 'failed':
|
||||
logger.warning(f" - {file_info['input']}: {file_info.get('error', 'Unknown error')}")
|
||||
|
||||
if results['successful'] > 0:
|
||||
logger.info(f"\n✅ Successfully processed {results['successful']} files!")
|
||||
|
||||
except KeyboardInterrupt:
|
||||
logger.info("\n⚠️ Process interrupted by user")
|
||||
sys.exit(1)
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Unexpected error: {str(e)}")
|
||||
sys.exit(1)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@ -15,6 +15,8 @@ services:
|
||||
LOG_PATH: /app/logs
|
||||
NVIDIA_VISIBLE_DEVICES: all
|
||||
NVIDIA_DRIVER_CAPABILITIES: compute,utility
|
||||
PORT_WHISPERLIVE: ${PORT_WHISPERLIVE}
|
||||
HTTP_PORT: ${HTTP_PORT:-8080}
|
||||
volumes:
|
||||
- ./models:/app/models
|
||||
- ./ssl:/app/ssl
|
||||
@ -26,11 +28,15 @@ services:
|
||||
- driver: nvidia
|
||||
count: 1
|
||||
capabilities: [gpu]
|
||||
options:
|
||||
memory: "4G" # Match the main docker-compose.yml allocation
|
||||
ports:
|
||||
- ${PORT_WHISPERLIVE}:${PORT_WHISPERLIVE}
|
||||
- "${PORT_WHISPERLIVE}:${PORT_WHISPERLIVE}"
|
||||
- "${HTTP_PORT:-8080}:8080"
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- audio-network
|
||||
- default
|
||||
|
||||
networks:
|
||||
audio-network:
|
||||
default:
|
||||
driver: bridge
|
||||
|
||||
1229
hybrid_server.py
Normal file
1229
hybrid_server.py
Normal file
File diff suppressed because it is too large
Load Diff
866
openapi.json
Normal file
866
openapi.json
Normal file
@ -0,0 +1,866 @@
|
||||
{
|
||||
"openapi": "3.1.0",
|
||||
"info": {
|
||||
"title": "WhisperLive API",
|
||||
"description": "A high-performance speech-to-text API based on OpenAI's Whisper model.\nSupports real-time transcription via WebSocket and batch processing via HTTP.\n\n## Features\n- Real-time audio transcription\n- Batch file processing\n- Multiple language support\n- Translation capabilities\n- Multiple model sizes\n- WebSocket and HTTP interfaces\n",
|
||||
"version": "1.0.0",
|
||||
"contact": {
|
||||
"name": "WhisperLive Support",
|
||||
"url": "https://github.com/collabora/WhisperLive"
|
||||
},
|
||||
"license": {
|
||||
"name": "MIT",
|
||||
"url": "https://opensource.org/licenses/MIT"
|
||||
}
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
"url": "http://localhost:8080",
|
||||
"description": "Local development server"
|
||||
},
|
||||
{
|
||||
"url": "https://api.whisperlive.com/v1",
|
||||
"description": "Production server"
|
||||
}
|
||||
],
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"paths": {
|
||||
"/v1/audio/transcriptions": {
|
||||
"post": {
|
||||
"summary": "Create transcription",
|
||||
"description": "Transcribes audio into the input language. The response will include the transcribed text\nand additional metadata such as language detection, confidence scores, and timestamps.\n",
|
||||
"operationId": "createTranscription",
|
||||
"tags": [
|
||||
"Audio"
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"multipart/form-data": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"required": [
|
||||
"file"
|
||||
],
|
||||
"properties": {
|
||||
"file": {
|
||||
"type": "string",
|
||||
"format": "binary",
|
||||
"description": "The audio file object (not file name) to transcribe, in one of these formats: \nflac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.\n"
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"tiny",
|
||||
"base",
|
||||
"small",
|
||||
"medium",
|
||||
"large"
|
||||
],
|
||||
"default": "base",
|
||||
"description": "ID of the model to use. Only whisper-1 is currently available."
|
||||
},
|
||||
"language": {
|
||||
"type": "string",
|
||||
"pattern": "^[a-z]{2}$",
|
||||
"description": "The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.\nSupported languages: en, es, fr, de, it, pt, ru, ja, ko, zh, hi, ar\n"
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "An optional text to guide the model's style or continue a previous audio segment.\nThe prompt should match the audio language.\n"
|
||||
},
|
||||
"response_format": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"json",
|
||||
"text",
|
||||
"srt",
|
||||
"verbose_json",
|
||||
"vtt"
|
||||
],
|
||||
"default": "json",
|
||||
"description": "The format of the transcript output."
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"maximum": 1,
|
||||
"default": 0,
|
||||
"description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic."
|
||||
},
|
||||
"timestamp_granularities": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"word",
|
||||
"segment"
|
||||
]
|
||||
},
|
||||
"description": "The timestamp granularities to populate for this transcription."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionTextResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionSrtResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionVttResponse"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest"
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"413": {
|
||||
"$ref": "#/components/responses/FileTooLarge"
|
||||
},
|
||||
"422": {
|
||||
"$ref": "#/components/responses/ValidationError"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/RateLimitExceeded"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/audio/translations": {
|
||||
"post": {
|
||||
"summary": "Create translation",
|
||||
"description": "Translates audio into English. The response will include the translated text\nand additional metadata such as confidence scores and timestamps.\n",
|
||||
"operationId": "createTranslation",
|
||||
"tags": [
|
||||
"Audio"
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"multipart/form-data": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"required": [
|
||||
"file"
|
||||
],
|
||||
"properties": {
|
||||
"file": {
|
||||
"type": "string",
|
||||
"format": "binary",
|
||||
"description": "The audio file object (not file name) to translate, in one of these formats: \nflac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.\n"
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"tiny",
|
||||
"base",
|
||||
"small",
|
||||
"medium",
|
||||
"large"
|
||||
],
|
||||
"default": "base",
|
||||
"description": "ID of the model to use. Only whisper-1 is currently available."
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "An optional text to guide the model's style or continue a previous audio segment.\nThe prompt should be in English.\n"
|
||||
},
|
||||
"response_format": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"json",
|
||||
"text",
|
||||
"srt",
|
||||
"verbose_json",
|
||||
"vtt"
|
||||
],
|
||||
"default": "json",
|
||||
"description": "The format of the transcript output."
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"minimum": 0,
|
||||
"maximum": 1,
|
||||
"default": 0,
|
||||
"description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic."
|
||||
},
|
||||
"timestamp_granularities": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"word",
|
||||
"segment"
|
||||
]
|
||||
},
|
||||
"description": "The timestamp granularities to populate for this translation."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionTextResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionSrtResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/TranscriptionVttResponse"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest"
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"413": {
|
||||
"$ref": "#/components/responses/FileTooLarge"
|
||||
},
|
||||
"422": {
|
||||
"$ref": "#/components/responses/ValidationError"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/RateLimitExceeded"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/models": {
|
||||
"get": {
|
||||
"summary": "List models",
|
||||
"description": "Lists the currently available models, and provides basic information about each one such as the owner and availability.",
|
||||
"operationId": "listModels",
|
||||
"tags": [
|
||||
"Models"
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ListModelsResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/models/{model}": {
|
||||
"get": {
|
||||
"summary": "Retrieve model",
|
||||
"description": "Retrieves a model instance, providing basic information about the model such as the owner and permissioning.",
|
||||
"operationId": "retrieveModel",
|
||||
"tags": [
|
||||
"Models"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "model",
|
||||
"in": "path",
|
||||
"required": true,
|
||||
"description": "The ID of the model to use for this request",
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"tiny",
|
||||
"base",
|
||||
"small",
|
||||
"medium",
|
||||
"large"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Model"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"404": {
|
||||
"$ref": "#/components/responses/NotFound"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/health": {
|
||||
"get": {
|
||||
"summary": "Health check",
|
||||
"description": "Check the health status of the API server",
|
||||
"operationId": "healthCheck",
|
||||
"tags": [
|
||||
"System"
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/HealthResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/websocket": {
|
||||
"get": {
|
||||
"summary": "WebSocket connection",
|
||||
"description": "Establishes a WebSocket connection for real-time audio transcription.\nSend audio data as binary frames and receive transcription results.\n",
|
||||
"operationId": "websocketConnection",
|
||||
"tags": [
|
||||
"Real-time"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "model",
|
||||
"in": "query",
|
||||
"description": "The model to use for transcription",
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"tiny",
|
||||
"base",
|
||||
"small",
|
||||
"medium",
|
||||
"large"
|
||||
],
|
||||
"default": "base"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "language",
|
||||
"in": "query",
|
||||
"description": "The language of the input audio",
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"pattern": "^[a-z]{2}$"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task",
|
||||
"in": "query",
|
||||
"description": "The task to perform",
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"transcribe",
|
||||
"translate"
|
||||
],
|
||||
"default": "transcribe"
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"101": {
|
||||
"description": "Switching Protocols",
|
||||
"headers": {
|
||||
"Upgrade": {
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"example": "websocket"
|
||||
}
|
||||
},
|
||||
"Connection": {
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"example": "Upgrade"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest"
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"components": {
|
||||
"securitySchemes": {
|
||||
"ApiKeyAuth": {
|
||||
"type": "apiKey",
|
||||
"in": "header",
|
||||
"name": "Authorization",
|
||||
"description": "API key authentication. Include your API key in the Authorization header.\nExample: `Authorization: Bearer your-api-key-here`\n"
|
||||
}
|
||||
},
|
||||
"schemas": {
|
||||
"TranscriptionResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"text": {
|
||||
"type": "string",
|
||||
"description": "The transcribed text"
|
||||
},
|
||||
"language": {
|
||||
"type": "string",
|
||||
"description": "The language of the input audio"
|
||||
},
|
||||
"duration": {
|
||||
"type": "number",
|
||||
"description": "The duration of the input audio in seconds"
|
||||
},
|
||||
"words": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/Word"
|
||||
},
|
||||
"description": "Extracted words and their corresponding timestamps"
|
||||
},
|
||||
"segments": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/Segment"
|
||||
},
|
||||
"description": "Segments of the transcribed text with timestamps"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"text"
|
||||
]
|
||||
},
|
||||
"TranscriptionTextResponse": {
|
||||
"type": "string",
|
||||
"description": "The transcribed text as plain text"
|
||||
},
|
||||
"TranscriptionSrtResponse": {
|
||||
"type": "string",
|
||||
"description": "The transcribed text in SRT subtitle format"
|
||||
},
|
||||
"TranscriptionVttResponse": {
|
||||
"type": "string",
|
||||
"description": "The transcribed text in VTT subtitle format"
|
||||
},
|
||||
"Word": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"word": {
|
||||
"type": "string",
|
||||
"description": "The text content of the word"
|
||||
},
|
||||
"start": {
|
||||
"type": "number",
|
||||
"description": "Start time of the word in seconds"
|
||||
},
|
||||
"end": {
|
||||
"type": "number",
|
||||
"description": "End time of the word in seconds"
|
||||
},
|
||||
"probability": {
|
||||
"type": "number",
|
||||
"description": "Confidence score of the word (0-1)"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"word",
|
||||
"start",
|
||||
"end"
|
||||
]
|
||||
},
|
||||
"Segment": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "integer",
|
||||
"description": "Unique identifier for the segment"
|
||||
},
|
||||
"seek": {
|
||||
"type": "number",
|
||||
"description": "Seek offset of the segment in seconds"
|
||||
},
|
||||
"start": {
|
||||
"type": "number",
|
||||
"description": "Start time of the segment in seconds"
|
||||
},
|
||||
"end": {
|
||||
"type": "number",
|
||||
"description": "End time of the segment in seconds"
|
||||
},
|
||||
"text": {
|
||||
"type": "string",
|
||||
"description": "The text content of the segment"
|
||||
},
|
||||
"tokens": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "integer"
|
||||
},
|
||||
"description": "Array of token IDs for the segment"
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "Temperature parameter used for generating this segment"
|
||||
},
|
||||
"avg_logprob": {
|
||||
"type": "number",
|
||||
"description": "Average log probability of the segment"
|
||||
},
|
||||
"compression_ratio": {
|
||||
"type": "number",
|
||||
"description": "Compression ratio of the segment"
|
||||
},
|
||||
"no_speech_prob": {
|
||||
"type": "number",
|
||||
"description": "Probability of no speech in this segment"
|
||||
},
|
||||
"words": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/Word"
|
||||
},
|
||||
"description": "Words in this segment"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"id",
|
||||
"seek",
|
||||
"start",
|
||||
"end",
|
||||
"text"
|
||||
]
|
||||
},
|
||||
"Model": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The model identifier"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"model"
|
||||
],
|
||||
"description": "The object type, which is always \"model\""
|
||||
},
|
||||
"created": {
|
||||
"type": "integer",
|
||||
"description": "The Unix timestamp (in seconds) when the model was created"
|
||||
},
|
||||
"owned_by": {
|
||||
"type": "string",
|
||||
"description": "The organization that owns the model"
|
||||
},
|
||||
"permission": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object"
|
||||
},
|
||||
"description": "The permissions associated with the model"
|
||||
},
|
||||
"root": {
|
||||
"type": "string",
|
||||
"description": "The root of the model"
|
||||
},
|
||||
"parent": {
|
||||
"type": "string",
|
||||
"description": "The parent of the model"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"id",
|
||||
"object",
|
||||
"created",
|
||||
"owned_by"
|
||||
]
|
||||
},
|
||||
"ListModelsResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"object": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"list"
|
||||
],
|
||||
"description": "The object type, which is always \"list\""
|
||||
},
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/Model"
|
||||
},
|
||||
"description": "The list of models"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"object",
|
||||
"data"
|
||||
]
|
||||
},
|
||||
"HealthResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"status": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"healthy",
|
||||
"unhealthy"
|
||||
],
|
||||
"description": "The health status of the service"
|
||||
},
|
||||
"service": {
|
||||
"type": "string",
|
||||
"description": "The name of the service"
|
||||
},
|
||||
"version": {
|
||||
"type": "string",
|
||||
"description": "The version of the service"
|
||||
},
|
||||
"timestamp": {
|
||||
"type": "string",
|
||||
"format": "date-time",
|
||||
"description": "The current timestamp"
|
||||
},
|
||||
"uptime": {
|
||||
"type": "number",
|
||||
"description": "The uptime in seconds"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"status",
|
||||
"service"
|
||||
]
|
||||
},
|
||||
"Error": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"error": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"message": {
|
||||
"type": "string",
|
||||
"description": "A human-readable error message"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"description": "The type of error"
|
||||
},
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The error code"
|
||||
},
|
||||
"param": {
|
||||
"type": "string",
|
||||
"description": "The parameter that caused the error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"error"
|
||||
]
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"BadRequest": {
|
||||
"description": "Bad Request",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "Invalid request parameters",
|
||||
"type": "invalid_request_error",
|
||||
"code": "invalid_parameters"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"Unauthorized": {
|
||||
"description": "Unauthorized",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "Invalid API key",
|
||||
"type": "authentication_error",
|
||||
"code": "invalid_api_key"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileTooLarge": {
|
||||
"description": "File Too Large",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "File size exceeds maximum allowed size",
|
||||
"type": "invalid_request_error",
|
||||
"code": "file_too_large"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"ValidationError": {
|
||||
"description": "Validation Error",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "Invalid file format",
|
||||
"type": "invalid_request_error",
|
||||
"code": "invalid_file_format"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"RateLimitExceeded": {
|
||||
"description": "Rate Limit Exceeded",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "Rate limit exceeded",
|
||||
"type": "rate_limit_error",
|
||||
"code": "rate_limit_exceeded"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"InternalServerError": {
|
||||
"description": "Internal Server Error",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "An internal server error occurred",
|
||||
"type": "server_error",
|
||||
"code": "internal_error"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"NotFound": {
|
||||
"description": "Not Found",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Error"
|
||||
},
|
||||
"example": {
|
||||
"error": {
|
||||
"message": "Model not found",
|
||||
"type": "invalid_request_error",
|
||||
"code": "model_not_found"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
{
|
||||
"name": "Audio",
|
||||
"description": "Audio transcription and translation operations"
|
||||
},
|
||||
{
|
||||
"name": "Models",
|
||||
"description": "Model management operations"
|
||||
},
|
||||
{
|
||||
"name": "System",
|
||||
"description": "System health and status operations"
|
||||
},
|
||||
{
|
||||
"name": "Real-time",
|
||||
"description": "Real-time audio processing via WebSocket"
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -9,5 +9,7 @@ av
|
||||
jiwer
|
||||
evaluate
|
||||
numpy<2
|
||||
openai-whisper==20240930
|
||||
tokenizers==0.20.3
|
||||
flask==3.0.0
|
||||
flask-sock
|
||||
websocket-client
|
||||
727
scratch/dashboard.html
Normal file
727
scratch/dashboard.html
Normal file
@ -0,0 +1,727 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>WhisperLive Dashboard</title>
|
||||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
|
||||
<style>
|
||||
:root {
|
||||
--primary: #4f46e5;
|
||||
--primary-hover: #4338ca;
|
||||
--bg-color: #0f172a;
|
||||
--card-bg: rgba(30, 41, 59, 0.7);
|
||||
--text-main: #f8fafc;
|
||||
--text-muted: #94a3b8;
|
||||
--border: rgba(255, 255, 255, 0.1);
|
||||
--success: #10b981;
|
||||
--danger: #ef4444;
|
||||
--warning: #f59e0b;
|
||||
}
|
||||
|
||||
* {
|
||||
box-sizing: border-box;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: 'Inter', sans-serif;
|
||||
background-color: var(--bg-color);
|
||||
color: var(--text-main);
|
||||
min-height: 100vh;
|
||||
background-image:
|
||||
radial-gradient(at 0% 0%, rgba(79, 70, 229, 0.15) 0px, transparent 50%),
|
||||
radial-gradient(at 100% 100%, rgba(16, 185, 129, 0.1) 0px, transparent 50%);
|
||||
background-attachment: fixed;
|
||||
padding: 2rem;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 1000px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.header {
|
||||
text-align: center;
|
||||
margin-bottom: 2rem;
|
||||
}
|
||||
|
||||
.header h1 {
|
||||
font-size: 2.5rem;
|
||||
font-weight: 700;
|
||||
background: linear-gradient(to right, #818cf8, #34d399);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.header p {
|
||||
color: var(--text-muted);
|
||||
}
|
||||
|
||||
.glass-panel {
|
||||
background: var(--card-bg);
|
||||
backdrop-filter: blur(12px);
|
||||
-webkit-backdrop-filter: blur(12px);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 1rem;
|
||||
padding: 1.5rem;
|
||||
margin-bottom: 1.5rem;
|
||||
box-shadow: 0 10px 25px -5px rgba(0, 0, 0, 0.3);
|
||||
}
|
||||
|
||||
/* Config Section */
|
||||
.config-grid {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr 1fr;
|
||||
gap: 1rem;
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
.config-grid {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
}
|
||||
|
||||
.form-group {
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
.form-group label {
|
||||
display: block;
|
||||
font-size: 0.875rem;
|
||||
font-weight: 500;
|
||||
margin-bottom: 0.5rem;
|
||||
color: var(--text-muted);
|
||||
}
|
||||
|
||||
input[type="text"],
|
||||
input[type="file"],
|
||||
select {
|
||||
width: 100%;
|
||||
padding: 0.75rem 1rem;
|
||||
background: rgba(15, 23, 42, 0.6);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 0.5rem;
|
||||
color: var(--text-main);
|
||||
font-size: 0.875rem;
|
||||
transition: all 0.2s;
|
||||
}
|
||||
|
||||
input[type="text"]:focus,
|
||||
select:focus {
|
||||
outline: none;
|
||||
border-color: var(--primary);
|
||||
box-shadow: 0 0 0 2px rgba(79, 70, 229, 0.2);
|
||||
}
|
||||
|
||||
/* Tabs */
|
||||
.tabs {
|
||||
display: flex;
|
||||
gap: 0.5rem;
|
||||
margin-bottom: 1rem;
|
||||
border-bottom: 1px solid var(--border);
|
||||
padding-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.tab-btn {
|
||||
background: transparent;
|
||||
border: none;
|
||||
color: var(--text-muted);
|
||||
padding: 0.75rem 1.5rem;
|
||||
font-size: 1rem;
|
||||
font-weight: 500;
|
||||
cursor: pointer;
|
||||
border-radius: 0.5rem;
|
||||
transition: all 0.2s;
|
||||
}
|
||||
|
||||
.tab-btn:hover {
|
||||
color: var(--text-main);
|
||||
background: rgba(255, 255, 255, 0.05);
|
||||
}
|
||||
|
||||
.tab-btn.active {
|
||||
color: var(--text-main);
|
||||
background: var(--primary);
|
||||
box-shadow: 0 4px 6px -1px rgba(79, 70, 229, 0.4);
|
||||
}
|
||||
|
||||
.tab-content {
|
||||
display: none;
|
||||
animation: fadeIn 0.3s ease-in-out;
|
||||
}
|
||||
|
||||
.tab-content.active {
|
||||
display: block;
|
||||
}
|
||||
|
||||
@keyframes fadeIn {
|
||||
from {
|
||||
opacity: 0;
|
||||
transform: translateY(5px);
|
||||
}
|
||||
|
||||
to {
|
||||
opacity: 1;
|
||||
transform: translateY(0);
|
||||
}
|
||||
}
|
||||
|
||||
/* Buttons */
|
||||
.btn {
|
||||
background: var(--primary);
|
||||
color: white;
|
||||
border: none;
|
||||
padding: 0.75rem 1.5rem;
|
||||
border-radius: 0.5rem;
|
||||
font-weight: 600;
|
||||
cursor: pointer;
|
||||
transition: all 0.2s;
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
gap: 0.5rem;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.btn:hover {
|
||||
background: var(--primary-hover);
|
||||
}
|
||||
|
||||
.btn:disabled {
|
||||
opacity: 0.5;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.btn-danger {
|
||||
background: var(--danger);
|
||||
}
|
||||
|
||||
.btn-danger:hover {
|
||||
background: #dc2626;
|
||||
}
|
||||
|
||||
.btn-success {
|
||||
background: var(--success);
|
||||
}
|
||||
|
||||
.btn-success:hover {
|
||||
background: #059669;
|
||||
}
|
||||
|
||||
/* Results / Live View */
|
||||
.transcript-box {
|
||||
background: rgba(15, 23, 42, 0.6);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 0.5rem;
|
||||
padding: 1.5rem;
|
||||
min-height: 200px;
|
||||
max-height: 400px;
|
||||
overflow-y: auto;
|
||||
margin-top: 1rem;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.segment {
|
||||
margin-bottom: 0.75rem;
|
||||
padding-bottom: 0.75rem;
|
||||
border-bottom: 1px solid rgba(255, 255, 255, 0.05);
|
||||
}
|
||||
|
||||
.segment:last-child {
|
||||
border-bottom: none;
|
||||
margin-bottom: 0;
|
||||
padding-bottom: 0;
|
||||
}
|
||||
|
||||
.segment-time {
|
||||
font-size: 0.75rem;
|
||||
color: var(--primary);
|
||||
font-weight: 600;
|
||||
margin-bottom: 0.25rem;
|
||||
}
|
||||
|
||||
.status-badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 0.3rem;
|
||||
padding: 0.25rem 0.75rem;
|
||||
border-radius: 9999px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.status-offline {
|
||||
background: rgba(239, 68, 68, 0.2);
|
||||
color: #fca5a5;
|
||||
}
|
||||
|
||||
.status-online {
|
||||
background: rgba(16, 185, 129, 0.2);
|
||||
color: #6ee7b7;
|
||||
}
|
||||
|
||||
.status-recording {
|
||||
background: rgba(239, 68, 68, 0.2);
|
||||
color: #fca5a5;
|
||||
animation: pulse 2s infinite;
|
||||
}
|
||||
|
||||
@keyframes pulse {
|
||||
0% {
|
||||
box-shadow: 0 0 0 0 rgba(239, 68, 68, 0.4);
|
||||
}
|
||||
|
||||
70% {
|
||||
box-shadow: 0 0 0 10px rgba(239, 68, 68, 0);
|
||||
}
|
||||
|
||||
100% {
|
||||
box-shadow: 0 0 0 0 rgba(239, 68, 68, 0);
|
||||
}
|
||||
}
|
||||
|
||||
/* Code snippets */
|
||||
pre {
|
||||
background: #1e293b;
|
||||
padding: 1rem;
|
||||
border-radius: 0.5rem;
|
||||
overflow-x: auto;
|
||||
font-size: 0.875rem;
|
||||
color: #e2e8f0;
|
||||
border: 1px solid var(--border);
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
code {
|
||||
font-family: 'Courier New', Courier, monospace;
|
||||
}
|
||||
|
||||
.loading-spinner {
|
||||
display: none;
|
||||
width: 24px;
|
||||
height: 24px;
|
||||
border: 3px solid rgba(255, 255, 255, 0.3);
|
||||
border-radius: 50%;
|
||||
border-top-color: white;
|
||||
animation: spin 1s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes spin {
|
||||
to {
|
||||
transform: rotate(360deg);
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<h1>WhisperLive</h1>
|
||||
<p>High-Performance Real-Time Audio Transcription</p>
|
||||
</div>
|
||||
|
||||
<!-- Configuration Panel -->
|
||||
<div class="glass-panel">
|
||||
<h3 style="margin-bottom: 1rem; font-size: 1.1rem;">Connection Settings</h3>
|
||||
<div class="config-grid">
|
||||
<div class="form-group">
|
||||
<label>HTTP API URL (For File Upload & API)</label>
|
||||
<input type="text" id="httpUrl" value="https://whisperlive.classroomcopilot.ai">
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>WebSocket URL (For Live Audio)</label>
|
||||
<input type="text" id="wsUrl" value="wss://whisperlive.classroomcopilot.ai/ws">
|
||||
</div>
|
||||
</div>
|
||||
<div style="margin-top: 0.5rem; font-size: 0.8rem; color: var(--text-muted);">
|
||||
HTTP Status: <span id="httpStatus" class="status-badge status-offline">Checking...</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Main Workspace -->
|
||||
<div class="glass-panel">
|
||||
<div class="tabs">
|
||||
<button class="tab-btn active" onclick="switchTab('file-tab')">File Upload</button>
|
||||
<button class="tab-btn" onclick="switchTab('live-tab')">Live Microphone</button>
|
||||
<button class="tab-btn" onclick="switchTab('api-tab')">API Usage</button>
|
||||
</div>
|
||||
|
||||
<!-- Tab 1: File Upload -->
|
||||
<div id="file-tab" class="tab-content active">
|
||||
<form id="fileForm">
|
||||
<div class="form-group">
|
||||
<label>Audio File</label>
|
||||
<input type="file" id="audioFile" accept=".wav,.mp3,.flac,.m4a,.ogg,.webm" required>
|
||||
</div>
|
||||
|
||||
<div class="config-grid">
|
||||
<div class="form-group">
|
||||
<label>Language</label>
|
||||
<select id="fileLanguage">
|
||||
<option value="">Auto-detect</option>
|
||||
<option value="en">English</option>
|
||||
<option value="es">Spanish</option>
|
||||
<option value="fr">French</option>
|
||||
</select>
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>Task</label>
|
||||
<select id="fileTask">
|
||||
<option value="transcribe">Transcribe</option>
|
||||
<option value="translate">Translate to English</option>
|
||||
</select>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<button type="submit" class="btn" id="fileSubmitBtn">
|
||||
<span>Transcribe File</span>
|
||||
<div class="loading-spinner" id="fileSpinner"></div>
|
||||
</button>
|
||||
</form>
|
||||
|
||||
<div id="fileResult" style="display: none;">
|
||||
<div class="transcript-box" id="fileTranscript"></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Tab 2: Live Recording -->
|
||||
<div id="live-tab" class="tab-content">
|
||||
<div class="config-grid" style="margin-bottom: 1.5rem;">
|
||||
<div class="form-group">
|
||||
<label>Language</label>
|
||||
<select id="liveLanguage">
|
||||
<option value="en">English</option>
|
||||
<option value="es">Spanish</option>
|
||||
<option value="fr">French</option>
|
||||
</select>
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>Task</label>
|
||||
<select id="liveTask">
|
||||
<option value="transcribe">Transcribe</option>
|
||||
<option value="translate">Translate to English</option>
|
||||
</select>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div style="display: flex; gap: 1rem; align-items: center;">
|
||||
<button id="recordBtn" class="btn btn-success" style="width: auto;">
|
||||
<span id="recordIcon">🎤</span> <span id="recordText">Start Recording</span>
|
||||
</button>
|
||||
<span id="liveStatus" class="status-badge status-offline" style="display: none;">Not
|
||||
connected</span>
|
||||
</div>
|
||||
|
||||
<div class="transcript-box" id="liveTranscript">
|
||||
<div style="color: var(--text-muted); text-align: center; margin-top: 3rem;">
|
||||
Click Start Recording to begin live transcription...
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Tab 3: API Usage -->
|
||||
<div id="api-tab" class="tab-content">
|
||||
<h3 style="margin-bottom: 1rem;">OpenAI Compatible API</h3>
|
||||
<p style="color: var(--text-muted); margin-bottom: 1rem; font-size: 0.9rem;">
|
||||
WhisperLive acts as a drop-in replacement for OpenAI's Whisper API. You can use any standard OpenAI
|
||||
client by changing the base URL.
|
||||
</p>
|
||||
|
||||
<h4 style="margin-bottom: 0.5rem; color: #cbd5e1;">Python (openai package)</h4>
|
||||
<pre><code id="pythonSnippet">from openai import OpenAI
|
||||
|
||||
client = OpenAI(
|
||||
api_key="sk-no-key-required",
|
||||
base_url="https://whisperlive.classroomcopilot.ai/v1/"
|
||||
)
|
||||
|
||||
with open("audio.wav", "rb") as file:
|
||||
transcription = client.audio.transcriptions.create(
|
||||
file=file,
|
||||
model="base",
|
||||
response_format="verbose_json"
|
||||
)
|
||||
|
||||
print(transcription.text)</code></pre>
|
||||
|
||||
<h4 style="margin-bottom: 0.5rem; color: #cbd5e1;">cURL</h4>
|
||||
<pre><code id="curlSnippet">curl https://whisperlive.classroomcopilot.ai/v1/audio/transcriptions \
|
||||
-H "Content-Type: multipart/form-data" \
|
||||
-F file="@audio.wav" \
|
||||
-F model="base" \
|
||||
-F response_format="verbose_json"</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script>
|
||||
// DOM Elements
|
||||
const httpUrlInput = document.getElementById('httpUrl');
|
||||
const wsUrlInput = document.getElementById('wsUrl');
|
||||
const httpStatus = document.getElementById('httpStatus');
|
||||
|
||||
// Initialization
|
||||
window.onload = () => {
|
||||
// Check if on same domain to set default URL intelligently, else leave defaults
|
||||
if (window.location.hostname !== '' && window.location.hostname !== 'localhost') {
|
||||
httpUrlInput.value = window.location.origin;
|
||||
wsUrlInput.value = window.location.origin.replace(/^http/, 'ws') + '/ws';
|
||||
}
|
||||
checkHealth();
|
||||
updateSnippets();
|
||||
};
|
||||
|
||||
httpUrlInput.addEventListener('change', () => { checkHealth(); updateSnippets(); });
|
||||
|
||||
// Tab Switching
|
||||
function switchTab(tabId) {
|
||||
document.querySelectorAll('.tab-content').forEach(t => t.classList.remove('active'));
|
||||
document.querySelectorAll('.tab-btn').forEach(b => b.classList.remove('active'));
|
||||
document.getElementById(tabId).classList.add('active');
|
||||
event.target.classList.add('active');
|
||||
}
|
||||
|
||||
// Health Check
|
||||
async function checkHealth() {
|
||||
try {
|
||||
const res = await fetch(`${httpUrlInput.value}/health`);
|
||||
if (res.ok) {
|
||||
httpStatus.className = 'status-badge status-online';
|
||||
httpStatus.textContent = '✅ Online';
|
||||
} else throw new Error();
|
||||
} catch (e) {
|
||||
httpStatus.className = 'status-badge status-offline';
|
||||
httpStatus.textContent = '❌ Offline';
|
||||
}
|
||||
}
|
||||
|
||||
// Update Code Snippets
|
||||
function updateSnippets() {
|
||||
const baseUrl = httpUrlInput.value.endsWith('/') ? httpUrlInput.value.slice(0, -1) : httpUrlInput.value;
|
||||
document.getElementById('pythonSnippet').textContent = `from openai import OpenAI\n\nclient = OpenAI(\n api_key="sk-no-key-required",\n base_url="${baseUrl}/v1/"\n)\n\nwith open("audio.wav", "rb") as file:\n transcription = client.audio.transcriptions.create(\n file=file,\n model="base",\n response_format="verbose_json"\n )\n \nprint(transcription.text)`;
|
||||
document.getElementById('curlSnippet').textContent = `curl ${baseUrl}/v1/audio/transcriptions \\\n -H "Content-Type: multipart/form-data" \\\n -F file="@audio.wav" \\\n -F model="base" \\\n -F response_format="verbose_json"`;
|
||||
}
|
||||
|
||||
// Utility: Format Time
|
||||
function formatTime(seconds) {
|
||||
if (!seconds) return "0:00";
|
||||
const mins = Math.floor(seconds / 60);
|
||||
const secs = (seconds % 60).toFixed(2);
|
||||
return `${mins}:${secs.padStart(5, '0')}`;
|
||||
}
|
||||
|
||||
// ==========================================
|
||||
// FEATURE 1: FILE TRANSCRIPTION
|
||||
// ==========================================
|
||||
document.getElementById('fileForm').addEventListener('submit', async (e) => {
|
||||
e.preventDefault();
|
||||
const file = document.getElementById('audioFile').files[0];
|
||||
if (!file) return;
|
||||
|
||||
const btn = document.getElementById('fileSubmitBtn');
|
||||
const spinner = document.getElementById('fileSpinner');
|
||||
const resultBox = document.getElementById('fileResult');
|
||||
const transcriptBox = document.getElementById('fileTranscript');
|
||||
|
||||
btn.disabled = true;
|
||||
spinner.style.display = 'block';
|
||||
resultBox.style.display = 'none';
|
||||
|
||||
const formData = new FormData();
|
||||
formData.append('file', file);
|
||||
formData.append('model', 'base');
|
||||
formData.append('response_format', 'verbose_json');
|
||||
|
||||
const lang = document.getElementById('fileLanguage').value;
|
||||
if (lang) formData.append('language', lang);
|
||||
|
||||
const task = document.getElementById('fileTask').value;
|
||||
const baseUrl = httpUrlInput.value.endsWith('/') ? httpUrlInput.value.slice(0, -1) : httpUrlInput.value;
|
||||
const endpoint = task === 'translate' ? `${baseUrl}/v1/audio/translations` : `${baseUrl}/v1/audio/transcriptions`;
|
||||
|
||||
try {
|
||||
const response = await fetch(endpoint, { method: 'POST', body: formData });
|
||||
const data = await response.json();
|
||||
|
||||
resultBox.style.display = 'block';
|
||||
if (response.ok) {
|
||||
let html = '';
|
||||
if (data.segments && data.segments.length > 0) {
|
||||
data.segments.forEach(seg => {
|
||||
html += `<div class="segment"><div class="segment-time">${formatTime(seg.start)} - ${formatTime(seg.end)}</div><div class="segment-text">${seg.text}</div></div>`;
|
||||
});
|
||||
} else if (data.text) {
|
||||
html += `<div class="segment"><div class="segment-text">${data.text}</div></div>`;
|
||||
}
|
||||
transcriptBox.innerHTML = html;
|
||||
} else {
|
||||
transcriptBox.innerHTML = `<div style="color: var(--danger)">Error: ${data.error?.message || JSON.stringify(data.error)}</div>`;
|
||||
}
|
||||
} catch (error) {
|
||||
resultBox.style.display = 'block';
|
||||
transcriptBox.innerHTML = `<div style="color: var(--danger)">Network Error: ${error.message}</div>`;
|
||||
} finally {
|
||||
btn.disabled = false;
|
||||
spinner.style.display = 'none';
|
||||
}
|
||||
});
|
||||
|
||||
// ==========================================
|
||||
// FEATURE 2: LIVE WEBSOCKET TRANSCRIPTION
|
||||
// ==========================================
|
||||
let ws = null;
|
||||
let audioContext = null;
|
||||
let mediaStream = null;
|
||||
let processor = null;
|
||||
let isRecording = false;
|
||||
|
||||
const recordBtn = document.getElementById('recordBtn');
|
||||
const liveStatus = document.getElementById('liveStatus');
|
||||
const liveTranscript = document.getElementById('liveTranscript');
|
||||
|
||||
recordBtn.addEventListener('click', async () => {
|
||||
if (isRecording) {
|
||||
stopRecording();
|
||||
} else {
|
||||
startRecording();
|
||||
}
|
||||
});
|
||||
|
||||
async function startRecording() {
|
||||
liveTranscript.innerHTML = '';
|
||||
liveStatus.style.display = 'inline-flex';
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Connecting...';
|
||||
|
||||
try {
|
||||
// 1. Connect WebSocket
|
||||
ws = new WebSocket(wsUrlInput.value);
|
||||
|
||||
ws.onopen = () => {
|
||||
// Send options to server
|
||||
const options = {
|
||||
uid: "web-" + Math.random().toString(36).substring(7),
|
||||
language: document.getElementById('liveLanguage').value,
|
||||
task: document.getElementById('liveTask').value,
|
||||
model: "base",
|
||||
use_vad: true
|
||||
};
|
||||
ws.send(JSON.stringify(options));
|
||||
};
|
||||
|
||||
ws.onmessage = async (event) => {
|
||||
const data = JSON.parse(event.data);
|
||||
|
||||
if (data.message === "SERVER_READY") {
|
||||
liveStatus.className = 'status-badge status-recording';
|
||||
liveStatus.innerHTML = '🔴 Recording';
|
||||
await startAudioCapture();
|
||||
} else if (data.segments) {
|
||||
renderLiveSegments(data.segments);
|
||||
} else if (data.status === "WAIT") {
|
||||
liveStatus.textContent = `Waiting in queue (Est: ${data.message} min)`;
|
||||
} else if (data.message === "DISCONNECT") {
|
||||
stopRecording();
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Disconnected by server';
|
||||
}
|
||||
};
|
||||
|
||||
ws.onerror = (err) => {
|
||||
console.error('WebSocket Error', err);
|
||||
stopRecording();
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Connection Error';
|
||||
};
|
||||
|
||||
ws.onclose = () => {
|
||||
stopRecording();
|
||||
};
|
||||
|
||||
// Update UI
|
||||
isRecording = true;
|
||||
recordBtn.className = 'btn btn-danger';
|
||||
document.getElementById('recordIcon').textContent = '⏹';
|
||||
document.getElementById('recordText').textContent = 'Stop Recording';
|
||||
|
||||
} catch (err) {
|
||||
console.error(err);
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Microphone Error';
|
||||
stopRecording();
|
||||
}
|
||||
}
|
||||
|
||||
async function startAudioCapture() {
|
||||
mediaStream = await navigator.mediaDevices.getUserMedia({ audio: true });
|
||||
audioContext = new (window.AudioContext || window.webkitAudioContext)({ sampleRate: 16000 });
|
||||
const source = audioContext.createMediaStreamSource(mediaStream);
|
||||
|
||||
// Create a ScriptProcessorNode with bufferSize of 4096 and a single input/output channel
|
||||
processor = audioContext.createScriptProcessor(4096, 1, 1);
|
||||
|
||||
processor.onaudioprocess = function (e) {
|
||||
if (!isRecording || ws.readyState !== WebSocket.OPEN) return;
|
||||
const float32Array = e.inputBuffer.getChannelData(0);
|
||||
ws.send(float32Array.buffer);
|
||||
};
|
||||
|
||||
source.connect(processor);
|
||||
processor.connect(audioContext.destination);
|
||||
}
|
||||
|
||||
function stopRecording() {
|
||||
isRecording = false;
|
||||
|
||||
if (processor) {
|
||||
processor.disconnect();
|
||||
processor = null;
|
||||
}
|
||||
if (mediaStream) {
|
||||
mediaStream.getTracks().forEach(track => track.stop());
|
||||
mediaStream = null;
|
||||
}
|
||||
if (audioContext) {
|
||||
audioContext.close();
|
||||
audioContext = null;
|
||||
}
|
||||
if (ws) {
|
||||
if (ws.readyState === WebSocket.OPEN) {
|
||||
ws.send("END_OF_AUDIO");
|
||||
setTimeout(() => ws.close(), 1000);
|
||||
}
|
||||
ws = null;
|
||||
}
|
||||
|
||||
recordBtn.className = 'btn btn-success';
|
||||
document.getElementById('recordIcon').textContent = '🎤';
|
||||
document.getElementById('recordText').textContent = 'Start Recording';
|
||||
|
||||
if (liveStatus.textContent === '🔴 Recording') {
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Stopped';
|
||||
}
|
||||
}
|
||||
|
||||
let liveSegments = [];
|
||||
function renderLiveSegments(segments) {
|
||||
let html = '';
|
||||
segments.forEach(seg => {
|
||||
const timeHtml = (seg.start !== undefined && seg.end !== undefined)
|
||||
? `<div class="segment-time">${formatTime(seg.start)} - ${formatTime(seg.end)}</div>`
|
||||
: '';
|
||||
html += `<div class="segment">${timeHtml}<div class="segment-text">${seg.text}</div></div>`;
|
||||
});
|
||||
liveTranscript.innerHTML = html;
|
||||
liveTranscript.scrollTop = liveTranscript.scrollHeight;
|
||||
}
|
||||
|
||||
</script>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
9
scratch/test_ws.py
Normal file
9
scratch/test_ws.py
Normal file
@ -0,0 +1,9 @@
|
||||
import websockets
|
||||
from websockets.sync.server import serve
|
||||
|
||||
def handler(websocket):
|
||||
print("Path:", websocket.request.path)
|
||||
websocket.send("Hello")
|
||||
|
||||
with serve(handler, "127.0.0.1", 8765) as server:
|
||||
server.serve_forever()
|
||||
727
test_form.html
Normal file
727
test_form.html
Normal file
@ -0,0 +1,727 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>WhisperLive Dashboard</title>
|
||||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
|
||||
<style>
|
||||
:root {
|
||||
--primary: #4f46e5;
|
||||
--primary-hover: #4338ca;
|
||||
--bg-color: #0f172a;
|
||||
--card-bg: rgba(30, 41, 59, 0.7);
|
||||
--text-main: #f8fafc;
|
||||
--text-muted: #94a3b8;
|
||||
--border: rgba(255, 255, 255, 0.1);
|
||||
--success: #10b981;
|
||||
--danger: #ef4444;
|
||||
--warning: #f59e0b;
|
||||
}
|
||||
|
||||
* {
|
||||
box-sizing: border-box;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: 'Inter', sans-serif;
|
||||
background-color: var(--bg-color);
|
||||
color: var(--text-main);
|
||||
min-height: 100vh;
|
||||
background-image:
|
||||
radial-gradient(at 0% 0%, rgba(79, 70, 229, 0.15) 0px, transparent 50%),
|
||||
radial-gradient(at 100% 100%, rgba(16, 185, 129, 0.1) 0px, transparent 50%);
|
||||
background-attachment: fixed;
|
||||
padding: 2rem;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 1000px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.header {
|
||||
text-align: center;
|
||||
margin-bottom: 2rem;
|
||||
}
|
||||
|
||||
.header h1 {
|
||||
font-size: 2.5rem;
|
||||
font-weight: 700;
|
||||
background: linear-gradient(to right, #818cf8, #34d399);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.header p {
|
||||
color: var(--text-muted);
|
||||
}
|
||||
|
||||
.glass-panel {
|
||||
background: var(--card-bg);
|
||||
backdrop-filter: blur(12px);
|
||||
-webkit-backdrop-filter: blur(12px);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 1rem;
|
||||
padding: 1.5rem;
|
||||
margin-bottom: 1.5rem;
|
||||
box-shadow: 0 10px 25px -5px rgba(0, 0, 0, 0.3);
|
||||
}
|
||||
|
||||
/* Config Section */
|
||||
.config-grid {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr 1fr;
|
||||
gap: 1rem;
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
.config-grid {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
}
|
||||
|
||||
.form-group {
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
.form-group label {
|
||||
display: block;
|
||||
font-size: 0.875rem;
|
||||
font-weight: 500;
|
||||
margin-bottom: 0.5rem;
|
||||
color: var(--text-muted);
|
||||
}
|
||||
|
||||
input[type="text"],
|
||||
input[type="file"],
|
||||
select {
|
||||
width: 100%;
|
||||
padding: 0.75rem 1rem;
|
||||
background: rgba(15, 23, 42, 0.6);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 0.5rem;
|
||||
color: var(--text-main);
|
||||
font-size: 0.875rem;
|
||||
transition: all 0.2s;
|
||||
}
|
||||
|
||||
input[type="text"]:focus,
|
||||
select:focus {
|
||||
outline: none;
|
||||
border-color: var(--primary);
|
||||
box-shadow: 0 0 0 2px rgba(79, 70, 229, 0.2);
|
||||
}
|
||||
|
||||
/* Tabs */
|
||||
.tabs {
|
||||
display: flex;
|
||||
gap: 0.5rem;
|
||||
margin-bottom: 1rem;
|
||||
border-bottom: 1px solid var(--border);
|
||||
padding-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
.tab-btn {
|
||||
background: transparent;
|
||||
border: none;
|
||||
color: var(--text-muted);
|
||||
padding: 0.75rem 1.5rem;
|
||||
font-size: 1rem;
|
||||
font-weight: 500;
|
||||
cursor: pointer;
|
||||
border-radius: 0.5rem;
|
||||
transition: all 0.2s;
|
||||
}
|
||||
|
||||
.tab-btn:hover {
|
||||
color: var(--text-main);
|
||||
background: rgba(255, 255, 255, 0.05);
|
||||
}
|
||||
|
||||
.tab-btn.active {
|
||||
color: var(--text-main);
|
||||
background: var(--primary);
|
||||
box-shadow: 0 4px 6px -1px rgba(79, 70, 229, 0.4);
|
||||
}
|
||||
|
||||
.tab-content {
|
||||
display: none;
|
||||
animation: fadeIn 0.3s ease-in-out;
|
||||
}
|
||||
|
||||
.tab-content.active {
|
||||
display: block;
|
||||
}
|
||||
|
||||
@keyframes fadeIn {
|
||||
from {
|
||||
opacity: 0;
|
||||
transform: translateY(5px);
|
||||
}
|
||||
|
||||
to {
|
||||
opacity: 1;
|
||||
transform: translateY(0);
|
||||
}
|
||||
}
|
||||
|
||||
/* Buttons */
|
||||
.btn {
|
||||
background: var(--primary);
|
||||
color: white;
|
||||
border: none;
|
||||
padding: 0.75rem 1.5rem;
|
||||
border-radius: 0.5rem;
|
||||
font-weight: 600;
|
||||
cursor: pointer;
|
||||
transition: all 0.2s;
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
gap: 0.5rem;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.btn:hover {
|
||||
background: var(--primary-hover);
|
||||
}
|
||||
|
||||
.btn:disabled {
|
||||
opacity: 0.5;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.btn-danger {
|
||||
background: var(--danger);
|
||||
}
|
||||
|
||||
.btn-danger:hover {
|
||||
background: #dc2626;
|
||||
}
|
||||
|
||||
.btn-success {
|
||||
background: var(--success);
|
||||
}
|
||||
|
||||
.btn-success:hover {
|
||||
background: #059669;
|
||||
}
|
||||
|
||||
/* Results / Live View */
|
||||
.transcript-box {
|
||||
background: rgba(15, 23, 42, 0.6);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 0.5rem;
|
||||
padding: 1.5rem;
|
||||
min-height: 200px;
|
||||
max-height: 400px;
|
||||
overflow-y: auto;
|
||||
margin-top: 1rem;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.segment {
|
||||
margin-bottom: 0.75rem;
|
||||
padding-bottom: 0.75rem;
|
||||
border-bottom: 1px solid rgba(255, 255, 255, 0.05);
|
||||
}
|
||||
|
||||
.segment:last-child {
|
||||
border-bottom: none;
|
||||
margin-bottom: 0;
|
||||
padding-bottom: 0;
|
||||
}
|
||||
|
||||
.segment-time {
|
||||
font-size: 0.75rem;
|
||||
color: var(--primary);
|
||||
font-weight: 600;
|
||||
margin-bottom: 0.25rem;
|
||||
}
|
||||
|
||||
.status-badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 0.3rem;
|
||||
padding: 0.25rem 0.75rem;
|
||||
border-radius: 9999px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.status-offline {
|
||||
background: rgba(239, 68, 68, 0.2);
|
||||
color: #fca5a5;
|
||||
}
|
||||
|
||||
.status-online {
|
||||
background: rgba(16, 185, 129, 0.2);
|
||||
color: #6ee7b7;
|
||||
}
|
||||
|
||||
.status-recording {
|
||||
background: rgba(239, 68, 68, 0.2);
|
||||
color: #fca5a5;
|
||||
animation: pulse 2s infinite;
|
||||
}
|
||||
|
||||
@keyframes pulse {
|
||||
0% {
|
||||
box-shadow: 0 0 0 0 rgba(239, 68, 68, 0.4);
|
||||
}
|
||||
|
||||
70% {
|
||||
box-shadow: 0 0 0 10px rgba(239, 68, 68, 0);
|
||||
}
|
||||
|
||||
100% {
|
||||
box-shadow: 0 0 0 0 rgba(239, 68, 68, 0);
|
||||
}
|
||||
}
|
||||
|
||||
/* Code snippets */
|
||||
pre {
|
||||
background: #1e293b;
|
||||
padding: 1rem;
|
||||
border-radius: 0.5rem;
|
||||
overflow-x: auto;
|
||||
font-size: 0.875rem;
|
||||
color: #e2e8f0;
|
||||
border: 1px solid var(--border);
|
||||
margin-bottom: 1rem;
|
||||
}
|
||||
|
||||
code {
|
||||
font-family: 'Courier New', Courier, monospace;
|
||||
}
|
||||
|
||||
.loading-spinner {
|
||||
display: none;
|
||||
width: 24px;
|
||||
height: 24px;
|
||||
border: 3px solid rgba(255, 255, 255, 0.3);
|
||||
border-radius: 50%;
|
||||
border-top-color: white;
|
||||
animation: spin 1s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes spin {
|
||||
to {
|
||||
transform: rotate(360deg);
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<h1>WhisperLive</h1>
|
||||
<p>High-Performance Real-Time Audio Transcription</p>
|
||||
</div>
|
||||
|
||||
<!-- Configuration Panel -->
|
||||
<div class="glass-panel">
|
||||
<h3 style="margin-bottom: 1rem; font-size: 1.1rem;">Connection Settings</h3>
|
||||
<div class="config-grid">
|
||||
<div class="form-group">
|
||||
<label>HTTP API URL (For File Upload & API)</label>
|
||||
<input type="text" id="httpUrl" value="https://whisperlive.classroomcopilot.ai">
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>WebSocket URL (For Live Audio)</label>
|
||||
<input type="text" id="wsUrl" value="wss://whisperlive.classroomcopilot.ai/ws">
|
||||
</div>
|
||||
</div>
|
||||
<div style="margin-top: 0.5rem; font-size: 0.8rem; color: var(--text-muted);">
|
||||
HTTP Status: <span id="httpStatus" class="status-badge status-offline">Checking...</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Main Workspace -->
|
||||
<div class="glass-panel">
|
||||
<div class="tabs">
|
||||
<button class="tab-btn active" onclick="switchTab('file-tab')">File Upload</button>
|
||||
<button class="tab-btn" onclick="switchTab('live-tab')">Live Microphone</button>
|
||||
<button class="tab-btn" onclick="switchTab('api-tab')">API Usage</button>
|
||||
</div>
|
||||
|
||||
<!-- Tab 1: File Upload -->
|
||||
<div id="file-tab" class="tab-content active">
|
||||
<form id="fileForm">
|
||||
<div class="form-group">
|
||||
<label>Audio File</label>
|
||||
<input type="file" id="audioFile" accept=".wav,.mp3,.flac,.m4a,.ogg,.webm" required>
|
||||
</div>
|
||||
|
||||
<div class="config-grid">
|
||||
<div class="form-group">
|
||||
<label>Language</label>
|
||||
<select id="fileLanguage">
|
||||
<option value="">Auto-detect</option>
|
||||
<option value="en">English</option>
|
||||
<option value="es">Spanish</option>
|
||||
<option value="fr">French</option>
|
||||
</select>
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>Task</label>
|
||||
<select id="fileTask">
|
||||
<option value="transcribe">Transcribe</option>
|
||||
<option value="translate">Translate to English</option>
|
||||
</select>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<button type="submit" class="btn" id="fileSubmitBtn">
|
||||
<span>Transcribe File</span>
|
||||
<div class="loading-spinner" id="fileSpinner"></div>
|
||||
</button>
|
||||
</form>
|
||||
|
||||
<div id="fileResult" style="display: none;">
|
||||
<div class="transcript-box" id="fileTranscript"></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Tab 2: Live Recording -->
|
||||
<div id="live-tab" class="tab-content">
|
||||
<div class="config-grid" style="margin-bottom: 1.5rem;">
|
||||
<div class="form-group">
|
||||
<label>Language</label>
|
||||
<select id="liveLanguage">
|
||||
<option value="en">English</option>
|
||||
<option value="es">Spanish</option>
|
||||
<option value="fr">French</option>
|
||||
</select>
|
||||
</div>
|
||||
<div class="form-group">
|
||||
<label>Task</label>
|
||||
<select id="liveTask">
|
||||
<option value="transcribe">Transcribe</option>
|
||||
<option value="translate">Translate to English</option>
|
||||
</select>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div style="display: flex; gap: 1rem; align-items: center;">
|
||||
<button id="recordBtn" class="btn btn-success" style="width: auto;">
|
||||
<span id="recordIcon">🎤</span> <span id="recordText">Start Recording</span>
|
||||
</button>
|
||||
<span id="liveStatus" class="status-badge status-offline" style="display: none;">Not
|
||||
connected</span>
|
||||
</div>
|
||||
|
||||
<div class="transcript-box" id="liveTranscript">
|
||||
<div style="color: var(--text-muted); text-align: center; margin-top: 3rem;">
|
||||
Click Start Recording to begin live transcription...
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Tab 3: API Usage -->
|
||||
<div id="api-tab" class="tab-content">
|
||||
<h3 style="margin-bottom: 1rem;">OpenAI Compatible API</h3>
|
||||
<p style="color: var(--text-muted); margin-bottom: 1rem; font-size: 0.9rem;">
|
||||
WhisperLive acts as a drop-in replacement for OpenAI's Whisper API. You can use any standard OpenAI
|
||||
client by changing the base URL.
|
||||
</p>
|
||||
|
||||
<h4 style="margin-bottom: 0.5rem; color: #cbd5e1;">Python (openai package)</h4>
|
||||
<pre><code id="pythonSnippet">from openai import OpenAI
|
||||
|
||||
client = OpenAI(
|
||||
api_key="sk-no-key-required",
|
||||
base_url="https://whisperlive.classroomcopilot.ai/v1/"
|
||||
)
|
||||
|
||||
with open("audio.wav", "rb") as file:
|
||||
transcription = client.audio.transcriptions.create(
|
||||
file=file,
|
||||
model="base",
|
||||
response_format="verbose_json"
|
||||
)
|
||||
|
||||
print(transcription.text)</code></pre>
|
||||
|
||||
<h4 style="margin-bottom: 0.5rem; color: #cbd5e1;">cURL</h4>
|
||||
<pre><code id="curlSnippet">curl https://whisperlive.classroomcopilot.ai/v1/audio/transcriptions \
|
||||
-H "Content-Type: multipart/form-data" \
|
||||
-F file="@audio.wav" \
|
||||
-F model="base" \
|
||||
-F response_format="verbose_json"</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script>
|
||||
// DOM Elements
|
||||
const httpUrlInput = document.getElementById('httpUrl');
|
||||
const wsUrlInput = document.getElementById('wsUrl');
|
||||
const httpStatus = document.getElementById('httpStatus');
|
||||
|
||||
// Initialization
|
||||
window.onload = () => {
|
||||
// Check if on same domain to set default URL intelligently, else leave defaults
|
||||
if (window.location.hostname !== '' && window.location.hostname !== 'localhost') {
|
||||
httpUrlInput.value = window.location.origin;
|
||||
wsUrlInput.value = window.location.origin.replace(/^http/, 'ws') + '/ws';
|
||||
}
|
||||
checkHealth();
|
||||
updateSnippets();
|
||||
};
|
||||
|
||||
httpUrlInput.addEventListener('change', () => { checkHealth(); updateSnippets(); });
|
||||
|
||||
// Tab Switching
|
||||
function switchTab(tabId) {
|
||||
document.querySelectorAll('.tab-content').forEach(t => t.classList.remove('active'));
|
||||
document.querySelectorAll('.tab-btn').forEach(b => b.classList.remove('active'));
|
||||
document.getElementById(tabId).classList.add('active');
|
||||
event.target.classList.add('active');
|
||||
}
|
||||
|
||||
// Health Check
|
||||
async function checkHealth() {
|
||||
try {
|
||||
const res = await fetch(`${httpUrlInput.value}/health`);
|
||||
if (res.ok) {
|
||||
httpStatus.className = 'status-badge status-online';
|
||||
httpStatus.textContent = '✅ Online';
|
||||
} else throw new Error();
|
||||
} catch (e) {
|
||||
httpStatus.className = 'status-badge status-offline';
|
||||
httpStatus.textContent = '❌ Offline';
|
||||
}
|
||||
}
|
||||
|
||||
// Update Code Snippets
|
||||
function updateSnippets() {
|
||||
const baseUrl = httpUrlInput.value.endsWith('/') ? httpUrlInput.value.slice(0, -1) : httpUrlInput.value;
|
||||
document.getElementById('pythonSnippet').textContent = `from openai import OpenAI\n\nclient = OpenAI(\n api_key="sk-no-key-required",\n base_url="${baseUrl}/v1/"\n)\n\nwith open("audio.wav", "rb") as file:\n transcription = client.audio.transcriptions.create(\n file=file,\n model="base",\n response_format="verbose_json"\n )\n \nprint(transcription.text)`;
|
||||
document.getElementById('curlSnippet').textContent = `curl ${baseUrl}/v1/audio/transcriptions \\\n -H "Content-Type: multipart/form-data" \\\n -F file="@audio.wav" \\\n -F model="base" \\\n -F response_format="verbose_json"`;
|
||||
}
|
||||
|
||||
// Utility: Format Time
|
||||
function formatTime(seconds) {
|
||||
if (!seconds) return "0:00";
|
||||
const mins = Math.floor(seconds / 60);
|
||||
const secs = (seconds % 60).toFixed(2);
|
||||
return `${mins}:${secs.padStart(5, '0')}`;
|
||||
}
|
||||
|
||||
// ==========================================
|
||||
// FEATURE 1: FILE TRANSCRIPTION
|
||||
// ==========================================
|
||||
document.getElementById('fileForm').addEventListener('submit', async (e) => {
|
||||
e.preventDefault();
|
||||
const file = document.getElementById('audioFile').files[0];
|
||||
if (!file) return;
|
||||
|
||||
const btn = document.getElementById('fileSubmitBtn');
|
||||
const spinner = document.getElementById('fileSpinner');
|
||||
const resultBox = document.getElementById('fileResult');
|
||||
const transcriptBox = document.getElementById('fileTranscript');
|
||||
|
||||
btn.disabled = true;
|
||||
spinner.style.display = 'block';
|
||||
resultBox.style.display = 'none';
|
||||
|
||||
const formData = new FormData();
|
||||
formData.append('file', file);
|
||||
formData.append('model', 'base');
|
||||
formData.append('response_format', 'verbose_json');
|
||||
|
||||
const lang = document.getElementById('fileLanguage').value;
|
||||
if (lang) formData.append('language', lang);
|
||||
|
||||
const task = document.getElementById('fileTask').value;
|
||||
const baseUrl = httpUrlInput.value.endsWith('/') ? httpUrlInput.value.slice(0, -1) : httpUrlInput.value;
|
||||
const endpoint = task === 'translate' ? `${baseUrl}/v1/audio/translations` : `${baseUrl}/v1/audio/transcriptions`;
|
||||
|
||||
try {
|
||||
const response = await fetch(endpoint, { method: 'POST', body: formData });
|
||||
const data = await response.json();
|
||||
|
||||
resultBox.style.display = 'block';
|
||||
if (response.ok) {
|
||||
let html = '';
|
||||
if (data.segments && data.segments.length > 0) {
|
||||
data.segments.forEach(seg => {
|
||||
html += `<div class="segment"><div class="segment-time">${formatTime(seg.start)} - ${formatTime(seg.end)}</div><div class="segment-text">${seg.text}</div></div>`;
|
||||
});
|
||||
} else if (data.text) {
|
||||
html += `<div class="segment"><div class="segment-text">${data.text}</div></div>`;
|
||||
}
|
||||
transcriptBox.innerHTML = html;
|
||||
} else {
|
||||
transcriptBox.innerHTML = `<div style="color: var(--danger)">Error: ${data.error?.message || JSON.stringify(data.error)}</div>`;
|
||||
}
|
||||
} catch (error) {
|
||||
resultBox.style.display = 'block';
|
||||
transcriptBox.innerHTML = `<div style="color: var(--danger)">Network Error: ${error.message}</div>`;
|
||||
} finally {
|
||||
btn.disabled = false;
|
||||
spinner.style.display = 'none';
|
||||
}
|
||||
});
|
||||
|
||||
// ==========================================
|
||||
// FEATURE 2: LIVE WEBSOCKET TRANSCRIPTION
|
||||
// ==========================================
|
||||
let ws = null;
|
||||
let audioContext = null;
|
||||
let mediaStream = null;
|
||||
let processor = null;
|
||||
let isRecording = false;
|
||||
|
||||
const recordBtn = document.getElementById('recordBtn');
|
||||
const liveStatus = document.getElementById('liveStatus');
|
||||
const liveTranscript = document.getElementById('liveTranscript');
|
||||
|
||||
recordBtn.addEventListener('click', async () => {
|
||||
if (isRecording) {
|
||||
stopRecording();
|
||||
} else {
|
||||
startRecording();
|
||||
}
|
||||
});
|
||||
|
||||
async function startRecording() {
|
||||
liveTranscript.innerHTML = '';
|
||||
liveStatus.style.display = 'inline-flex';
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Connecting...';
|
||||
|
||||
try {
|
||||
// 1. Connect WebSocket
|
||||
ws = new WebSocket(wsUrlInput.value);
|
||||
|
||||
ws.onopen = () => {
|
||||
// Send options to server
|
||||
const options = {
|
||||
uid: "web-" + Math.random().toString(36).substring(7),
|
||||
language: document.getElementById('liveLanguage').value,
|
||||
task: document.getElementById('liveTask').value,
|
||||
model: "base",
|
||||
use_vad: true
|
||||
};
|
||||
ws.send(JSON.stringify(options));
|
||||
};
|
||||
|
||||
ws.onmessage = async (event) => {
|
||||
const data = JSON.parse(event.data);
|
||||
|
||||
if (data.message === "SERVER_READY") {
|
||||
liveStatus.className = 'status-badge status-recording';
|
||||
liveStatus.innerHTML = '🔴 Recording';
|
||||
await startAudioCapture();
|
||||
} else if (data.segments) {
|
||||
renderLiveSegments(data.segments);
|
||||
} else if (data.status === "WAIT") {
|
||||
liveStatus.textContent = `Waiting in queue (Est: ${data.message} min)`;
|
||||
} else if (data.message === "DISCONNECT") {
|
||||
stopRecording();
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Disconnected by server';
|
||||
}
|
||||
};
|
||||
|
||||
ws.onerror = (err) => {
|
||||
console.error('WebSocket Error', err);
|
||||
stopRecording();
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Connection Error';
|
||||
};
|
||||
|
||||
ws.onclose = () => {
|
||||
stopRecording();
|
||||
};
|
||||
|
||||
// Update UI
|
||||
isRecording = true;
|
||||
recordBtn.className = 'btn btn-danger';
|
||||
document.getElementById('recordIcon').textContent = '⏹';
|
||||
document.getElementById('recordText').textContent = 'Stop Recording';
|
||||
|
||||
} catch (err) {
|
||||
console.error(err);
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Microphone Error';
|
||||
stopRecording();
|
||||
}
|
||||
}
|
||||
|
||||
async function startAudioCapture() {
|
||||
mediaStream = await navigator.mediaDevices.getUserMedia({ audio: true });
|
||||
audioContext = new (window.AudioContext || window.webkitAudioContext)({ sampleRate: 16000 });
|
||||
const source = audioContext.createMediaStreamSource(mediaStream);
|
||||
|
||||
// Create a ScriptProcessorNode with bufferSize of 4096 and a single input/output channel
|
||||
processor = audioContext.createScriptProcessor(4096, 1, 1);
|
||||
|
||||
processor.onaudioprocess = function (e) {
|
||||
if (!isRecording || ws.readyState !== WebSocket.OPEN) return;
|
||||
const float32Array = e.inputBuffer.getChannelData(0);
|
||||
ws.send(float32Array.buffer);
|
||||
};
|
||||
|
||||
source.connect(processor);
|
||||
processor.connect(audioContext.destination);
|
||||
}
|
||||
|
||||
function stopRecording() {
|
||||
isRecording = false;
|
||||
|
||||
if (processor) {
|
||||
processor.disconnect();
|
||||
processor = null;
|
||||
}
|
||||
if (mediaStream) {
|
||||
mediaStream.getTracks().forEach(track => track.stop());
|
||||
mediaStream = null;
|
||||
}
|
||||
if (audioContext) {
|
||||
audioContext.close();
|
||||
audioContext = null;
|
||||
}
|
||||
if (ws) {
|
||||
if (ws.readyState === WebSocket.OPEN) {
|
||||
ws.send("END_OF_AUDIO");
|
||||
setTimeout(() => ws.close(), 1000);
|
||||
}
|
||||
ws = null;
|
||||
}
|
||||
|
||||
recordBtn.className = 'btn btn-success';
|
||||
document.getElementById('recordIcon').textContent = '🎤';
|
||||
document.getElementById('recordText').textContent = 'Start Recording';
|
||||
|
||||
if (liveStatus.textContent === '🔴 Recording') {
|
||||
liveStatus.className = 'status-badge status-offline';
|
||||
liveStatus.textContent = 'Stopped';
|
||||
}
|
||||
}
|
||||
|
||||
let liveSegments = [];
|
||||
function renderLiveSegments(segments) {
|
||||
let html = '';
|
||||
segments.forEach(seg => {
|
||||
const timeHtml = (seg.start !== undefined && seg.end !== undefined)
|
||||
? `<div class="segment-time">${formatTime(seg.start)} - ${formatTime(seg.end)}</div>`
|
||||
: '';
|
||||
html += `<div class="segment">${timeHtml}<div class="segment-text">${seg.text}</div></div>`;
|
||||
});
|
||||
liveTranscript.innerHTML = html;
|
||||
liveTranscript.scrollTop = liveTranscript.scrollHeight;
|
||||
}
|
||||
|
||||
</script>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
159
test_http_endpoints.py
Normal file
159
test_http_endpoints.py
Normal file
@ -0,0 +1,159 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Test script for WhisperLive HTTP endpoints
|
||||
This script demonstrates how to use the new HTTP API for file transcription
|
||||
"""
|
||||
|
||||
import requests
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# Configuration
|
||||
HTTP_BASE_URL = "http://localhost:8080" # Adjust if using different port
|
||||
WEBSOCKET_PORT = 5050 # Your existing WebSocket port
|
||||
|
||||
def test_health_endpoint():
|
||||
"""Test the health check endpoint"""
|
||||
print("Testing health endpoint...")
|
||||
try:
|
||||
response = requests.get(f"{HTTP_BASE_URL}/health")
|
||||
print(f"Status: {response.status_code}")
|
||||
print(f"Response: {response.json()}")
|
||||
return response.status_code == 200
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
return False
|
||||
|
||||
def test_file_transcription(audio_file_path, language=None, task="transcribe", model="base"):
|
||||
"""Test file transcription endpoint"""
|
||||
print(f"\nTesting file transcription endpoint...")
|
||||
print(f"File: {audio_file_path}")
|
||||
print(f"Language: {language or 'auto-detect'}")
|
||||
print(f"Task: {task}")
|
||||
print(f"Model: {model}")
|
||||
|
||||
if not os.path.exists(audio_file_path):
|
||||
print(f"Error: File {audio_file_path} not found")
|
||||
return False
|
||||
|
||||
try:
|
||||
# Prepare the request
|
||||
files = {'file': open(audio_file_path, 'rb')}
|
||||
data = {
|
||||
'language': language,
|
||||
'task': task,
|
||||
'model': model
|
||||
}
|
||||
|
||||
# Make the request
|
||||
response = requests.post(f"{HTTP_BASE_URL}/transcribe", files=files, data=data)
|
||||
|
||||
print(f"Status: {response.status_code}")
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
print("Transcription successful!")
|
||||
print(f"Filename: {result.get('filename')}")
|
||||
print(f"Language: {result['info'].get('language')}")
|
||||
print(f"Duration: {result['info'].get('duration')} seconds")
|
||||
print(f"Number of segments: {len(result['segments'])}")
|
||||
|
||||
# Print first few segments
|
||||
for i, segment in enumerate(result['segments'][:3]):
|
||||
print(f"Segment {i+1}: [{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}")
|
||||
|
||||
if len(result['segments']) > 3:
|
||||
print(f"... and {len(result['segments']) - 3} more segments")
|
||||
|
||||
return True
|
||||
else:
|
||||
print(f"Error: {response.text}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
return False
|
||||
|
||||
def test_url_transcription():
|
||||
"""Test URL transcription endpoint (placeholder)"""
|
||||
print(f"\nTesting URL transcription endpoint...")
|
||||
try:
|
||||
data = {
|
||||
'url': 'https://example.com/audio.mp3',
|
||||
'language': 'en',
|
||||
'task': 'transcribe',
|
||||
'model': 'base'
|
||||
}
|
||||
|
||||
response = requests.post(f"{HTTP_BASE_URL}/transcribe/url", json=data)
|
||||
print(f"Status: {response.status_code}")
|
||||
print(f"Response: {response.json()}")
|
||||
return response.status_code == 200
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
return False
|
||||
|
||||
def test_openai_endpoint(audio_file_path):
|
||||
"""Test the OpenAI compatible endpoint"""
|
||||
print(f"\nTesting OpenAI compatible endpoint...")
|
||||
print(f"File: {audio_file_path}")
|
||||
|
||||
if not os.path.exists(audio_file_path):
|
||||
print(f"Error: File {audio_file_path} not found")
|
||||
return False
|
||||
|
||||
try:
|
||||
files = {'file': open(audio_file_path, 'rb')}
|
||||
data = {
|
||||
'model': 'whisper-1',
|
||||
'response_format': 'json'
|
||||
}
|
||||
|
||||
response = requests.post(f"{HTTP_BASE_URL}/v1/audio/transcriptions", files=files, data=data)
|
||||
print(f"Status: {response.status_code}")
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
print("OpenAI endpoint successful!")
|
||||
print(f"Response: {result}")
|
||||
return True
|
||||
else:
|
||||
print(f"Error: {response.text}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
return False
|
||||
|
||||
def main():
|
||||
"""Main test function"""
|
||||
print("WhisperLive HTTP Endpoints Test")
|
||||
print("=" * 40)
|
||||
|
||||
# Test health endpoint
|
||||
if not test_health_endpoint():
|
||||
print("Health check failed. Make sure the server is running.")
|
||||
return
|
||||
|
||||
# Test file transcription with a sample audio file
|
||||
# You can replace this with any audio file you have
|
||||
sample_audio = "assets/jfk.flac" # Adjust path as needed
|
||||
|
||||
if os.path.exists(sample_audio):
|
||||
test_file_transcription(sample_audio, language="en", task="transcribe", model="base")
|
||||
test_openai_endpoint(sample_audio)
|
||||
else:
|
||||
print(f"\nSample audio file not found at {sample_audio}")
|
||||
print("You can test with any audio file by calling:")
|
||||
print("test_file_transcription('path/to/your/audio.wav')")
|
||||
|
||||
# Test URL transcription endpoint
|
||||
test_url_transcription()
|
||||
|
||||
print("\n" + "=" * 40)
|
||||
print("Test completed!")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Loading…
x
Reference in New Issue
Block a user