5roop commited on
Commit
eda11f1
1 Parent(s): 3ce07ee

Prepared for changing ownership to CLASSLA

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -14,7 +14,7 @@ widget:
14
  src: https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020570a.flac.wav
15
  ---
16
 
17
- # wav2vec2-large-juznevesti
18
 
19
  This model for Serbian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 58 hours of audio and transcripts from [Južne vesti](https://www.juznevesti.com/), programme '15 minuta'.
20
 
@@ -45,8 +45,8 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
45
 
46
  # load model and tokenizer
47
  processor = Wav2Vec2Processor.from_pretrained(
48
- "5roop/wav2vec2-xls-r-juznevesti-sr")
49
- model = Wav2Vec2ForCTC.from_pretrained("5roop/wav2vec2-xls-r-juznevesti-sr")
50
 
51
 
52
  # download the example wav files:
 
14
  src: https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020570a.flac.wav
15
  ---
16
 
17
+ # wav2vec2-xls-r-juznevesti
18
 
19
  This model for Serbian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 58 hours of audio and transcripts from [Južne vesti](https://www.juznevesti.com/), programme '15 minuta'.
20
 
 
45
 
46
  # load model and tokenizer
47
  processor = Wav2Vec2Processor.from_pretrained(
48
+ "classla/wav2vec2-xls-r-juznevesti-sr")
49
+ model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-xls-r-juznevesti-sr")
50
 
51
 
52
  # download the example wav files: