Hugging Face's logo

airesearch
/
wav2vec2-large-xlsr-53-th

Automatic Speech Recognition
Transformers
PyTorch
Thai
wav2vec2
audio
hf-asr-leaderboard
robust-speech-event
speech
xlsr-fine-tuning
Eval Results (legacy)
Model card Files
xet
 Community
4
cstorm125 commited on
Commit
fc2a52a
·
1 Parent(s): f82bd96

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -19,8 +19,8 @@ We finetune [wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-la
19
 
20
  ```
21
  #load pretrained processor and model
22
- processor = Wav2Vec2Processor.from_pretrained("vistec-ai/wav2vec2-large-xlsr-53-th")
23
- model = Wav2Vec2ForCTC.from_pretrained("vistec-ai/wav2vec2-large-xlsr-53-th")
24
 
25
  #function to resample to 16_000
26
  def speech_file_to_array_fn(batch,
 
19
 
20
  ```
21
  #load pretrained processor and model
22
+ processor = Wav2Vec2Processor.from_pretrained("airesearch/wav2vec2-large-xlsr-53-th")
23
+ model = Wav2Vec2ForCTC.from_pretrained("airesearch/wav2vec2-large-xlsr-53-th")
24
 
25
  #function to resample to 16_000
26
  def speech_file_to_array_fn(batch,