Instructions to use espnet/owsm_v4_base_102M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/owsm_v4_base_102M with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_v4_base_102M" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,7 +65,12 @@ It supports the following speech-to-text tasks:
|
|
| 65 |
#### OWSM v4
|
| 66 |
|
| 67 |
```BibTex
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
```
|
| 70 |
|
| 71 |
#### OWSM-CTC
|
|
|
|
| 65 |
#### OWSM v4
|
| 66 |
|
| 67 |
```BibTex
|
| 68 |
+
@inproceedings{owsm-v4,
|
| 69 |
+
title={{OWSM} v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning},
|
| 70 |
+
author={Yifan Peng and Shakeel Muhammad and Yui Sudo and William Chen and Jinchuan Tian and Chyi-Jiunn Lin and Shinji Watanabe},
|
| 71 |
+
booktitle={Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH) (accepted)},
|
| 72 |
+
year={2025},
|
| 73 |
+
}
|
| 74 |
```
|
| 75 |
|
| 76 |
#### OWSM-CTC
|