Instructions to use Ducnt17/ChunkFormer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use Ducnt17/ChunkFormer with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "Ducnt17/ChunkFormer" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,8 @@ language:
|
|
| 7 |
pipeline_tag: automatic-speech-recognition
|
| 8 |
metrics:
|
| 9 |
- wer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
|
|
|
| 7 |
pipeline_tag: automatic-speech-recognition
|
| 8 |
metrics:
|
| 9 |
- wer
|
| 10 |
+
base_model:
|
| 11 |
+
- nvidia/stt_ru_conformer_ctc_large
|
| 12 |
+
tags:
|
| 13 |
+
- audio
|
| 14 |
---
|