Dymas/whisper-api-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add models url

Browse Source
This commit is contained in:
Serge Zaigraeff
2025-03-02 12:39:11 +03:00
parent eed8dd2813
commit 9207892552
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -160,6 +160,10 @@ You can use any Whisper model by changing the `model_path` in the configuration:
2. Update the `model_path` in `config.json` 2. Update the `model_path` in `config.json`
3. Restart the service 3. Restart the service
#### Recommended Models
For Russian language transcription, we recommend using the [**whisper-large-v3-russian**](https://huggingface.co/antony66/whisper-large-v3-russian) model from Hugging Face. This model is fine-tuned specifically for Russian speech recognition and delivers high accuracy. For faster transcription with slightly lower accuracy, consider the [**whisper-large-v3-turbo-russian**](https://huggingface.co/dvislobokov/whisper-large-v3-turbo-russian) model, which is optimized for speed.
### Hardware Acceleration ### Hardware Acceleration
The service automatically selects the best available compute device: The service automatically selects the best available compute device:
@@ -185,10 +189,6 @@ For slow transcription:
- Adjust `chunk_length_s` and `batch_size` parameters - Adjust `chunk_length_s` and `batch_size` parameters
- Consider using a smaller Whisper model - Consider using a smaller Whisper model
## License
[MIT License](LICENSE)
## Acknowledgements ## Acknowledgements
- OpenAI for the Whisper model - OpenAI for the Whisper model