|
--- |
|
license: apache-2.0 |
|
language: |
|
- ru |
|
library_name: transformers |
|
pipeline_tag: automatic-speech-recognition |
|
base_model: openai/whisper-base |
|
--- |
|
|
|
# Whisper-base-ru-pruned |
|
This is a pruned version of openai/whisper-base model with only russian tokens left. |
|
Pruning was made without any fine-tuning. Method from [this post](https://medium.com/m/global-identity-2?redirectUrl=https%3A%2F%2Ftowardsdatascience.com%2Fhow-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90) was used. |
|
|
|
Model size is 30% less then original whisper-base: |
|
| | openai/whisper-base | waveletdeboshir/whisper-base-ru-pruned | |
|
| :------ | :------ | :------ | |
|
| n of parameters | 74 M | 48.5 M | |
|
| n of parameters (with proj_out layer) | 99 M | 51 M | |
|
| model file size | 290 Mb | 203 Mb | |
|
|
|
|
