Automatic Speech Recognition
NeMo
PyTorch
Persian
speech
audio
CTC
Transducer
FastConformer
Transformer
NeMo
Eval Results (legacy)
Instructions to use nvidia/stt_fa_fastconformer_hybrid_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_fa_fastconformer_hybrid_large with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_fa_fastconformer_hybrid_large") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -82,7 +82,8 @@ asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_na
|
|
| 82 |
### Transcribing using Python
|
| 83 |
Having instantiated the model, simply do:
|
| 84 |
```
|
| 85 |
-
asr_model.transcribe([
|
|
|
|
| 86 |
```
|
| 87 |
|
| 88 |
### Transcribing many audio files
|
|
|
|
| 82 |
### Transcribing using Python
|
| 83 |
Having instantiated the model, simply do:
|
| 84 |
```
|
| 85 |
+
output = asr_model.transcribe(['sample.wav'])
|
| 86 |
+
print(output[0].text)
|
| 87 |
```
|
| 88 |
|
| 89 |
### Transcribing many audio files
|