From da6c8d25e444e536324ec281ad85b49230ca5f1a Mon Sep 17 00:00:00 2001 From: Quentin Fuxa Date: Fri, 3 Jan 2025 14:54:29 +0100 Subject: [PATCH] Update README.md --- README.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 838d464..2b445b5 100644 --- a/README.md +++ b/README.md @@ -2,13 +2,15 @@ This project extends the [Whisper Streaming](https://github.com/ufal/whisper_streaming) implementation by incorporating few extras. The enhancements include: -1. **Efficient FastAPI Server with WebSocket Endpoint**: Real-time speech-to-text transcription for browsers, web apps, or React Native, with audio chunks processed via FFmpeg async streaming process to ensure minimal latency. +1. **FastAPI Server with WebSocket Endpoint**: Real-time STT in browsers. Audio chunks processed via FFmpeg async streaming process. -2. **Buffering preview**: Enhances streaming feedback by displaying the unvalidated buffer content, allowing users to see live processing updates. +2. **Buffering preview**: Enhances streaming feedback by displaying the unvalidated buffer content. -3. **Javascript Client implementation**: Functionnal and minimalist MediaRecorder implementation that can be copied on your client side. +3. **Multiple users**: The backend can support multiple users simultaneously without conflicts. -4. **MLX Whisper backend**: Integrates the alternative backend option MLX Whisper, optimized for efficient speech recognition on Apple silicon. +4. **Javascript Client implementation**: MediaRecorder implementation that can be copied on your client side. + +5. **MLX Whisper backend**: Integrates the alternative backend option MLX Whisper, optimized for efficient speech recognition on Apple silicon. ![Demo Screenshot](src/demo.png)