Update README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ This project extends the [Whisper Streaming](https://github.com/ufal/whisper_str
|
|
6 |
|
7 |
2. **Buffering Indication**: Improves streaming display by showing the current processing status, providing users with immediate feedback.
|
8 |
|
9 |
-
3. **Javascript Client implementation**: Functionnal and minimalist MediaRecorder implementation that can be copied on your client side
|
10 |
|
11 |
4. **MLX Whisper backend**: Integrates the alternative backend option MLX Whisper, optimized for efficient speech recognition on Apple silicon.
|
12 |
|
@@ -25,21 +25,41 @@ This project extends the [Whisper Streaming](https://github.com/ufal/whisper_str
|
|
25 |
|
26 |
### How to Launch the Server
|
27 |
|
28 |
-
1. **
|
|
|
|
|
29 |
|
30 |
```bash
|
31 |
-
|
|
|
|
|
|
|
|
|
32 |
```
|
33 |
-
|
34 |
|
35 |
-
|
36 |
-
whisper
|
37 |
-
whisper-timestamped
|
38 |
-
faster-whisper (faster backend on NVIDIA GPU)
|
39 |
-
mlx-whisper (faster backend on Apple Silicon)
|
|
|
|
|
|
|
|
|
40 |
|
41 |
-
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
|
45 |
3. **Run the FastAPI Server**:
|
|
|
6 |
|
7 |
2. **Buffering Indication**: Improves streaming display by showing the current processing status, providing users with immediate feedback.
|
8 |
|
9 |
+
3. **Javascript Client implementation**: Functionnal and minimalist MediaRecorder implementation that can be copied on your client side.
|
10 |
|
11 |
4. **MLX Whisper backend**: Integrates the alternative backend option MLX Whisper, optimized for efficient speech recognition on Apple silicon.
|
12 |
|
|
|
25 |
|
26 |
### How to Launch the Server
|
27 |
|
28 |
+
1. **Dependencies**:
|
29 |
+
|
30 |
+
- Install required dependences :
|
31 |
|
32 |
```bash
|
33 |
+
# Whisper streaming required dependencies
|
34 |
+
pip install librosa soundfile
|
35 |
+
|
36 |
+
# Whisper streaming web required dependencies
|
37 |
+
pip install fastapi ffmpeg
|
38 |
```
|
39 |
+
- Install at least one whisper backend among:
|
40 |
|
41 |
+
```
|
42 |
+
whisper
|
43 |
+
whisper-timestamped
|
44 |
+
faster-whisper (faster backend on NVIDIA GPU)
|
45 |
+
mlx-whisper (faster backend on Apple Silicon)
|
46 |
+
|
47 |
+
and torch if you want to use VAC (Voice Activity Controller)
|
48 |
+
```
|
49 |
+
- Optionnal dependencies
|
50 |
|
51 |
+
```
|
52 |
+
# If you want to use VAC (Voice Activity Controller)
|
53 |
+
torch
|
54 |
+
|
55 |
+
# If you choose sentences as buffer trimming strategy
|
56 |
+
mosestokenizer
|
57 |
+
wtpsplit
|
58 |
+
tokenize_uk # If you work with Ukrainian text
|
59 |
+
|
60 |
+
# If you want to run the server using uvicorn (recommended)
|
61 |
+
uvicorn
|
62 |
+
```
|
63 |
|
64 |
|
65 |
3. **Run the FastAPI Server**:
|