antony66 commited on
Commit
86d6dd3
1 Parent(s): a607ab6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -7,7 +7,7 @@ tags:
7
  - whisper
8
  - russian
9
  datasets:
10
- - mozilla-foundation/common_voice_11_0
11
  metrics:
12
  - wer
13
  ---
@@ -16,9 +16,10 @@ metrics:
16
 
17
  This is a version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) finetuned for better support of Russian language.
18
 
19
- Dataset used for finetuning is Common Voice 11.0, Russian part.
20
 
21
- After preprocessing of the original dataset (train + test + validation splits were mixed and split to a new train + test split by 0.95/0.05) the original Whisper v3 has WER 9.2 while the finetuned version shows 6.31 (so far).
 
22
 
23
  ## Usage
24
 
 
7
  - whisper
8
  - russian
9
  datasets:
10
+ - mozilla-foundation/common_voice_17_0
11
  metrics:
12
  - wer
13
  ---
 
16
 
17
  This is a version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) finetuned for better support of Russian language.
18
 
19
+ Dataset used for finetuning is Common Voice 17.0, Russian part, that contains over 200k rows.
20
 
21
+ After preprocessing of the original dataset (all splits were mixed and splited to a new train + test split by 0.95/0.05,
22
+ that is 225761/11883 rows respectively) the original Whisper v3 has WER 9.84 while the finetuned version shows 6.39 (so far).
23
 
24
  ## Usage
25