on1onmangoes commited on
Commit
c030400
·
verified ·
1 Parent(s): 6ccbb9d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +76 -12
README.md CHANGED
@@ -4,26 +4,90 @@ emoji: 🎙️
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: gradio
7
- sdk_version: 3.50.2
8
  app_file: gradio_app.py
9
  pinned: false
10
  ---
11
 
12
- # Real-time Speech Transcription with FastRTC and Whisper
13
 
14
- This application provides real-time speech transcription using FastRTC for audio streaming and Whisper for speech recognition.
15
 
16
  ## Features
17
- - Real-time audio streaming
 
18
  - Voice Activity Detection (VAD)
19
- - Multi-language support
20
- - Low latency transcription
21
-
22
- ## Usage
23
- 1. Click the microphone button to start recording
24
- 2. Speak into your microphone
25
- 3. See your speech transcribed in real-time
26
- 4. Click the microphone button again to stop recording
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
 
28
  ## Technical Details
29
  - Uses FastRTC for WebRTC streaming
 
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: gradio
7
+ sdk_version: 4.19.2
8
  app_file: gradio_app.py
9
  pinned: false
10
  ---
11
 
12
+ # Real-time Transcription with FastRTC
13
 
14
+ This project implements real-time audio transcription using FastRTC and Gradio, deployed on Hugging Face Spaces.
15
 
16
  ## Features
17
+
18
+ - Real-time audio transcription
19
  - Voice Activity Detection (VAD)
20
+ - Web-based interface using Gradio
21
+ - Deployed on Hugging Face Spaces
22
+
23
+ ## Prerequisites
24
+
25
+ - Python 3.8 or higher
26
+ - Hugging Face account and token
27
+ - Git
28
+
29
+ ## Setup
30
+
31
+ 1. Clone the repository:
32
+ ```bash
33
+ git clone <your-repo-url>
34
+ cd realtime-transcription-fastrtc
35
+ ```
36
+
37
+ 2. Create a `.env` file with your Hugging Face credentials:
38
+ ```
39
+ HUGGINGFACE_TOKEN=your_token_here
40
+ HUGGINGFACE_USERNAME=your_username_here
41
+ ```
42
+
43
+ 3. Install dependencies:
44
+ ```bash
45
+ pip install -r requirements.txt
46
+ ```
47
+
48
+ ## Deployment
49
+
50
+ 1. Make sure you have set up your `.env` file with the required credentials.
51
+
52
+ 2. Run the deployment script:
53
+ ```bash
54
+ python deploy.py
55
+ ```
56
+
57
+ The script will:
58
+ - Check for required environment variables
59
+ - Install dependencies
60
+ - Log in to Hugging Face
61
+ - Create a new Space
62
+ - Deploy your application
63
+
64
+ 3. Once deployed, your application will be available at:
65
+ ```
66
+ https://huggingface.co/spaces/<your-username>/realtime-transcription
67
+ ```
68
+
69
+ ## Local Development
70
+
71
+ To run the application locally:
72
+
73
+ ```bash
74
+ python app.py
75
+ ```
76
+
77
+ The application will be available at `http://localhost:7860`
78
+
79
+ ## Troubleshooting
80
+
81
+ If you encounter any issues during deployment:
82
+
83
+ 1. Check that your Hugging Face token is valid and has the necessary permissions
84
+ 2. Ensure all dependencies are installed correctly
85
+ 3. Verify that your `.env` file contains the correct credentials
86
+ 4. Check the Hugging Face Spaces logs for any deployment errors
87
+
88
+ ## License
89
+
90
+ This project is licensed under the MIT License - see the LICENSE file for details.
91
 
92
  ## Technical Details
93
  - Uses FastRTC for WebRTC streaming