waveletdeboshir
/

whisper-tiny-ru-pruned

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Community

waveletdeboshir commited on Aug 13

Commit

65aa48f

•

1 Parent(s): b2e33cd

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ Pruning was made without any fine-tuning. Method from [this post](https://medium
 ## Size
 Only 10% tokens was left including special whisper tokens, added whisper tokens, 100 most popular tokens from tokenizer and 3000 most popular Russian tokens computed by tokenization of russian text corpus.
-Model size is 50%  less then original whisper-small:
 |  | openai/whisper-tiny | waveletdeboshir/whisper-tiny-ru-pruned |
 | :------ | :------ | :------ |
 | n of parameters | 38 M | 19.6 M |

 ## Size
 Only 10% tokens was left including special whisper tokens, added whisper tokens, 100 most popular tokens from tokenizer and 3000 most popular Russian tokens computed by tokenization of russian text corpus.
+Model size is 50%  less then original whisper-tiny:
 |  | openai/whisper-tiny | waveletdeboshir/whisper-tiny-ru-pruned |
 | :------ | :------ | :------ |
 | n of parameters | 38 M | 19.6 M |