alvanlii
/

distil-whisper-small-cantonese

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

alvanlii commited on Apr 4

Commit

243cd15

•

1 Parent(s): 748391b

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -50,8 +50,9 @@ For evaluation, Common Voice 16.0 yue Test set is used.
 |GPU Inference time (sdpa) [s/sample]|0.039|0.055|
 |GPU Inference (regular) [s/sample]|0.041|0.308|
 |CPU Inference [s/sample]|1.7|2.57|
-- inference time is calculated by taking the average inference time for the CV16 yue test set
 ## Using the Model
 ```

 |GPU Inference time (sdpa) [s/sample]|0.039|0.055|
 |GPU Inference (regular) [s/sample]|0.041|0.308|
 |CPU Inference [s/sample]|1.7|2.57|
+|Params [M]|157|242|
+Note: inference time is calculated by taking the average inference time for the CV16 yue test set
 ## Using the Model
 ```