Alikhan Urumov commited on
Commit
63ee913
1 Parent(s): f2ac8a1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -2,7 +2,7 @@
2
  tags:
3
  - generated_from_trainer
4
  model-index:
5
- - name: wav2vec2-russian
6
  results: []
7
  widget:
8
  - src: https://cdn-media.huggingface.co/speech_samples/common_voice_ru_18849022.mp3
@@ -12,7 +12,7 @@ widget:
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # wav2vec2-russian
16
  #
17
 
18
  модель для распознания аудио. результаты модели можно потом прогнать через мою сеть исправления текстов UrukHan/t5-russian-spell
@@ -38,8 +38,8 @@ should probably proofread and complete it, then remove this comment. -->
38
  #
39
  ```python
40
  from transformers import AutoModelForCTC, Wav2Vec2Processor
41
- model = AutoModelForCTC.from_pretrained("UrukHan/wav2vec2-russian")
42
- processor = Wav2Vec2Processor.from_pretrained("UrukHan/wav2vec2-russian")
43
  def map_to_result(batch):
44
  with torch.no_grad():
45
  input_values = torch.tensor(batch["input_values"]).unsqueeze(0) #, device="cuda"
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
5
+ - name: wav2vec2-ru
6
  results: []
7
  widget:
8
  - src: https://cdn-media.huggingface.co/speech_samples/common_voice_ru_18849022.mp3
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # wav2vec2-ru
16
  #
17
 
18
  модель для распознания аудио. результаты модели можно потом прогнать через мою сеть исправления текстов UrukHan/t5-russian-spell
 
38
  #
39
  ```python
40
  from transformers import AutoModelForCTC, Wav2Vec2Processor
41
+ model = AutoModelForCTC.from_pretrained("UrukHan/wav2vec2-ru")
42
+ processor = Wav2Vec2Processor.from_pretrained("UrukHan/wav2vec2-ru")
43
  def map_to_result(batch):
44
  with torch.no_grad():
45
  input_values = torch.tensor(batch["input_values"]).unsqueeze(0) #, device="cuda"