Yehor Smoliakov commited on
Commit
3b1124d
1 Parent(s): 76ee3fe
README.md CHANGED
@@ -15,13 +15,10 @@ Without LM:
15
  - WER: 0.2933
16
  - CER: 0.0539
17
 
18
- SMALL LM (https://huggingface.co/Yehor/wav2vec2-xls-r-300m-uk-with-small-lm):
 
 
19
 
20
  - WER: 0.1674
21
  - CER: 0.0332
22
 
23
- Wiki LM (this repository):
24
-
25
- - WER: 0.2936
26
- - CER: 0.0506
27
-
15
  - WER: 0.2933
16
  - CER: 0.0539
17
 
18
+ ---
19
+
20
+ SMALL LM:
21
 
22
  - WER: 0.1674
23
  - CER: 0.0332
24
 
 
 
 
 
 
language_model/uk_wiki.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b42b92b0312337d100daa64b78a4eaa52fa0a37d51a2e4a130bbd0acddefc5f1
3
- size 2267739501
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e73dfbd0052280ff72ad959cc96dc10207b557279770bcb5eeeaab004e401e
3
+ size 5687784056
language_model/unigrams.txt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7846e8f04f522f11357a54d37e78fe214c0e76f95d070f582384ea0f330877e2
3
- size 1428008
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2f184bae5d248d11381f0d80e96cbb61475c606dc58b93376d8ae7b4ae333b
3
+ size 73486450
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "name_or_path": "Yehor/wav2vec2-xls-r-300m-uk-with-wiki-lm", "processor_class": "Wav2Vec2ProcessorWithLM", "special_tokens_map_file": null, "tokenizer_class": "Wav2Vec2CTCTokenizer"}
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "name_or_path": "Yehor/wav2vec2-xls-r-300m-uk-with-wiki-lm", "processor_class": "Wav2Vec2ProcessorWithLM", "special_tokens_map_file": null, "tokenizer_class": "Wav2Vec2CTCTokenizer"}