Automatic Speech Recognition
NeMo
PyTorch
Chinese
speech
audio
CTC
Citrinet
NeMo
hf-asr-leaderboard
Riva
Eval Results (legacy)
Instructions to use nvidia/stt_zh_citrinet_1024_gamma_0_25 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_zh_citrinet_1024_gamma_0_25 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_zh_citrinet_1024_gamma_0_25") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -147,7 +147,8 @@ First, let's get a sample of spoken Mandarin Chinese.
|
|
| 147 |
|
| 148 |
Then simply do:
|
| 149 |
```
|
| 150 |
-
asr_model.transcribe(['
|
|
|
|
| 151 |
```
|
| 152 |
|
| 153 |
### Transcribing many audio files
|
|
|
|
| 147 |
|
| 148 |
Then simply do:
|
| 149 |
```
|
| 150 |
+
output = asr_model.transcribe(['sample.wav'])
|
| 151 |
+
print(output[0].text)
|
| 152 |
```
|
| 153 |
|
| 154 |
### Transcribing many audio files
|