Merge branch 'main' of https://github.com/microsoft/SpeechT5

microsoft · Apr 9, 2023 · 4e19cf4 · 4e19cf4
2 parents a2293c5 + 82e5749
commit 4e19cf4
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/SpeechLM/README.md b/SpeechLM/README.md
@@ -29,7 +29,7 @@
 
 
 ## Extract features using pre-trained models
-For easier use of our pre-trained models, we merge all inference-related code to [`SpeechLM.py`](SpeechLM.py) and make cleaned checkpoints [`SpeechLM-P Base`](https://msranlcmtteamdrive.blob.core.windows.net/share/speechlm/speechlmp_base_checkpoint_clean.pt?sv=2020-10-02&st=2022-10-13T06%3A15%3A13Z&se=2023-10-14T06%3A15%3A00Z&sr=c&sp=rl&sig=b0RFMEsG5ch3OA2%2FTTsoG5DFnLTE9c%2BeHKFJKcHI3Xg%3D) [`SpeechLM-H Base`](https://msranlcmtteamdrive.blob.core.windows.net/share/speechlm/speechlmh_base_checkpoint_clean.pt?sv=2020-10-02&st=2022-10-13T06%3A15%3A13Z&se=2023-10-14T06%3A15%3A00Z&sr=c&sp=rl&sig=b0RFMEsG5ch3OA2%2FTTsoG5DFnLTE9c%2BeHKFJKcHI3Xg%3D) [`SpeechLM-P Large`](https://msranlcmtteamdrive.blob.core.windows.net/share/speechlm/speechlmp_large_checkpoint_clean.pt?sv=2020-10-02&st=2022-10-13T06%3A15%3A13Z&se=2023-10-14T06%3A15%3A00Z&sr=c&sp=rl&sig=b0RFMEsG5ch3OA2%2FTTsoG5DFnLTE9c%2BeHKFJKcHI3Xg%3D) by removing non-required modules. Now you can directly use the following script to extract your speech features:
+For easier use of our pre-trained models, we merge all inference-related code to [`SpeechLM.py`](SpeechLM.py) and make cleaned checkpoints [`SpeechLM-P Base`](https://valle.blob.core.windows.net/share/speechlm/speechlmp_base_checkpoint_clean.pt?sv=2020-04-08&st=2023-04-04T05%3A42%3A17Z&se=2033-04-05T05%3A42%3A00Z&sr=b&sp=r&sig=DN7VwaEWhrhRPiyuT84mJpohrMeJsEPq4o6qRr8BNsk%3D) [`SpeechLM-H Base`](https://valle.blob.core.windows.net/share/speechlm/speechlmh_base_checkpoint_clean.pt?sv=2020-04-08&st=2023-04-04T05%3A43%3A07Z&se=2033-04-05T05%3A43%3A00Z&sr=b&sp=r&sig=T9oaIvrb3z3Wo5GTZp8eP2x7B7yuQ%2B80Ff1KhuWrrKg%3D) [`SpeechLM-P Large`](https://valle.blob.core.windows.net/share/speechlm/speechlmp_large_checkpoint_clean.pt?sv=2020-04-08&st=2023-04-04T05%3A43%3A33Z&se=2033-04-05T05%3A43%3A00Z&sr=b&sp=r&sig=qfWBNdiIGuDgkgUiHXaWnPiVbUHm3VSp%2FHTlWrCghRk%3D) by removing non-required modules. Now you can directly use the following script to extract your speech features:
 ```python
 import torch
 import torch.nn.functional as F