Automatic Speech Recognition
NeMo
Hindi
hindi
asr
speech
conformer
rnnt
varuna
Eval Results (legacy)
Instructions to use SkunkWorkLabs/varuna-stt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use SkunkWorkLabs/varuna-stt with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("SkunkWorkLabs/varuna-stt") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Add contact email for fine-tuning help
Browse files
README.md
CHANGED
|
@@ -248,6 +248,11 @@ for the reference implementation.
|
|
| 248 |
- 🧪 **Vistaar normalizer reference:** [AI4Bharat/vistaar](https://github.com/AI4Bharat/vistaar)
|
| 249 |
- 🛠 **Base model:** [nvidia/nemotron-speech-streaming-en-0.6b](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b)
|
| 250 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 251 |
## 📝 Citation
|
| 252 |
|
| 253 |
If you use Varuna STT in research or production, please cite:
|
|
|
|
| 248 |
- 🧪 **Vistaar normalizer reference:** [AI4Bharat/vistaar](https://github.com/AI4Bharat/vistaar)
|
| 249 |
- 🛠 **Base model:** [nvidia/nemotron-speech-streaming-en-0.6b](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b)
|
| 250 |
|
| 251 |
+
## 📬 Contact
|
| 252 |
+
|
| 253 |
+
Need help with the **training recipe** or want to **fine-tune Varuna** on
|
| 254 |
+
your own data? Reach out: **harshris2314@gmail.com**.
|
| 255 |
+
|
| 256 |
## 📝 Citation
|
| 257 |
|
| 258 |
If you use Varuna STT in research or production, please cite:
|