Instructions to use LocalDoc/speakwrite-azerbaijani with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use LocalDoc/speakwrite-azerbaijani with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("LocalDoc/speakwrite-azerbaijani") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -96,6 +96,12 @@ About 2800 hours of Azerbaijani speech. Encoder initialized from
|
|
| 96 |
[nvidia/stt_en_fastconformer_ctc_large](https://huggingface.co/nvidia/stt_en_fastconformer_ctc_large), then modified and trained for 4.5 epochs
|
| 97 |
(127552 updates) with the balbal-v2-manas recipe. balbal's own weights were not used.
|
| 98 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
## License
|
| 100 |
|
| 101 |
[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/). Non-commercial use only; credit is required in any project using this model:
|
|
|
|
| 96 |
[nvidia/stt_en_fastconformer_ctc_large](https://huggingface.co/nvidia/stt_en_fastconformer_ctc_large), then modified and trained for 4.5 epochs
|
| 97 |
(127552 updates) with the balbal-v2-manas recipe. balbal's own weights were not used.
|
| 98 |
|
| 99 |
+
|
| 100 |
+
## Acknowledgements
|
| 101 |
+
|
| 102 |
+
The ONNX graphs and the `pip install balbal` setup were contributed by [erayyapagci](https://huggingface.co/erayyapagci), the author of [balbal](https://github.com/erayyap/balbal).
|
| 103 |
+
|
| 104 |
+
|
| 105 |
## License
|
| 106 |
|
| 107 |
[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/). Non-commercial use only; credit is required in any project using this model:
|