Automatic Speech Recognition
ESPnet
multilingual
audio
speech-translation
language-identification
pyf98 commited on
Commit
a4fed36
·
verified ·
1 Parent(s): 3be41af

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -1
README.md CHANGED
@@ -160,7 +160,43 @@ print(segments)
160
 
161
 
162
 
163
- ## Citations
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
164
 
165
  #### OWSM-CTC
166
 
 
160
 
161
 
162
 
163
+ ### OWSM series
164
+
165
+ #### Encoder-decoder OWSM
166
+
167
+ | Name | Size | Hugging Face Repo |
168
+ | :--- | ---: | :---------------- |
169
+ | OWSM v3.1 base | 101M | https://huggingface.co/espnet/owsm_v3.1_ebf_base |
170
+ | OWSM v3.1 small | 367M | https://huggingface.co/espnet/owsm_v3.1_ebf_small |
171
+ | OWSM v3.1 medium | 1.02B | https://huggingface.co/espnet/owsm_v3.1_ebf |
172
+ | OWSM v3.2 small | 367M | https://huggingface.co/espnet/owsm_v3.2 |
173
+ | OWSM v4 base | 102M | https://huggingface.co/espnet/owsm_v4_base_102M |
174
+ | OWSM v4 small | 370M | https://huggingface.co/espnet/owsm_v4_small_370M |
175
+ | OWSM v4 medium | 1.02B | https://huggingface.co/espnet/owsm_v4_medium_1B |
176
+
177
+
178
+ #### CTC-based OWSM
179
+
180
+ | Name | Size | Hugging Face Repo |
181
+ | :--- | ---: | :---------------- |
182
+ | OWSM-CTC v3.1 medium | 1.01B | https://huggingface.co/espnet/owsm_ctc_v3.1_1B |
183
+ | OWSM-CTC v3.2 medium | 1.01B | https://huggingface.co/espnet/owsm_ctc_v3.2_ft_1B |
184
+ | OWSM-CTC v4 medium | 1.01B | https://huggingface.co/espnet/owsm_ctc_v4_1B |
185
+
186
+
187
+
188
+ ### Citations
189
+
190
+ #### OWSM v4
191
+
192
+ ```BibTex
193
+ @inproceedings{owsm-v4,
194
+ title={{OWSM} v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning},
195
+ author={Yifan Peng and Shakeel Muhammad and Yui Sudo and William Chen and Jinchuan Tian and Chyi-Jiunn Lin and Shinji Watanabe},
196
+ booktitle={Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH) (accepted)},
197
+ year={2025},
198
+ }
199
+ ```
200
 
201
  #### OWSM-CTC
202