Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- he
|
| 5 |
+
base_model:
|
| 6 |
+
- openai/whisper-large-v3-turbo
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
This is ivrit.ai's faster-whisper model, based on the ivrit-ai/yi-whisper-large-v3-turbo Whisper model.
|
| 10 |
+
|
| 11 |
+
# Prerequisites
|
| 12 |
+
|
| 13 |
+
pip3 install faster_whisper
|
| 14 |
+
|
| 15 |
+
# Usage
|
| 16 |
+
|
| 17 |
+
```
|
| 18 |
+
import faster_whisper
|
| 19 |
+
model = faster_whisper.WhisperModel('ivrit-ai/yi-whisper-large-v3-turbo-ct2')
|
| 20 |
+
|
| 21 |
+
segs, _ = model.transcribe('media-file', language='he')
|
| 22 |
+
|
| 23 |
+
texts = [s.text for s in segs]
|
| 24 |
+
|
| 25 |
+
transcribed_text = ' '.join(texts)
|
| 26 |
+
print(f'Transcribed text: {transcribed_text}')
|
| 27 |
+
```
|