Spaces:
Sleeping
Sleeping
Update readme.md
Browse files
readme.md
CHANGED
|
@@ -1,37 +1,10 @@
|
|
| 1 |
---
|
| 2 |
title: Accent Classifier
|
| 3 |
emoji: 🎙️
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: cyan
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: "3.38.1"
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
-
|
| 12 |
-
# Accent Classifier 🎙️
|
| 13 |
-
|
| 14 |
-
This app downloads a public YouTube or Vimeo video, extracts its audio, and classifies the speaker's accent (or rather, speaker ID as a proxy) using a Hugging Face model.
|
| 15 |
-
|
| 16 |
-
### How it works
|
| 17 |
-
|
| 18 |
-
1. You provide a video URL.
|
| 19 |
-
2. The app downloads the audio using `yt-dlp`.
|
| 20 |
-
3. It extracts the audio in a format suitable for the model (`wav`, 16kHz, mono).
|
| 21 |
-
4. It runs the `superb/wav2vec2-base-superb-sid` model to classify the speaker.
|
| 22 |
-
5. Displays the predicted speaker ID and confidence.
|
| 23 |
-
|
| 24 |
-
### Requirements
|
| 25 |
-
|
| 26 |
-
- Python 3.8+
|
| 27 |
-
- `yt-dlp`
|
| 28 |
-
- `ffmpeg` installed on your system and accessible from the command line.
|
| 29 |
-
- `gradio` for the UI.
|
| 30 |
-
- `transformers` from Hugging Face.
|
| 31 |
-
|
| 32 |
-
### Usage
|
| 33 |
-
|
| 34 |
-
Run the app:
|
| 35 |
-
|
| 36 |
-
```bash
|
| 37 |
-
python app.py
|
|
|
|
| 1 |
---
|
| 2 |
title: Accent Classifier
|
| 3 |
emoji: 🎙️
|
| 4 |
+
colorFrom: indigo
|
| 5 |
colorTo: cyan
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: "3.38.1"
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|