Automatic Speech Recognition
NeMo
PyTorch
Polish
speech
audio
Transducer
FastConformer
CTC
Transformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use nvidia/stt_pl_fastconformer_hybrid_large_pc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_pl_fastconformer_hybrid_large_pc with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_pl_fastconformer_hybrid_large_pc") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ library_name: nemo
|
|
| 5 |
datasets:
|
| 6 |
- multilingual_librispeech
|
| 7 |
- mozilla-foundation/common_voice_12_0
|
| 8 |
-
- VoxPopuli
|
| 9 |
thumbnail: null
|
| 10 |
tags:
|
| 11 |
- automatic-speech-recognition
|
|
@@ -150,7 +150,8 @@ wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
|
|
| 150 |
```
|
| 151 |
Then simply do:
|
| 152 |
```
|
| 153 |
-
asr_model.transcribe(['2086-149220-0033.wav'])
|
|
|
|
| 154 |
```
|
| 155 |
|
| 156 |
### Transcribing many audio files
|
|
|
|
| 5 |
datasets:
|
| 6 |
- multilingual_librispeech
|
| 7 |
- mozilla-foundation/common_voice_12_0
|
| 8 |
+
- VoxPopuli
|
| 9 |
thumbnail: null
|
| 10 |
tags:
|
| 11 |
- automatic-speech-recognition
|
|
|
|
| 150 |
```
|
| 151 |
Then simply do:
|
| 152 |
```
|
| 153 |
+
output = asr_model.transcribe(['2086-149220-0033.wav'])
|
| 154 |
+
print(output[0].text)
|
| 155 |
```
|
| 156 |
|
| 157 |
### Transcribing many audio files
|