Hugging Face's logo

Edresson
/
wav2vec2-large-100k-voxpopuli-ft-Common_Voice_plus_TTS-Dataset_plus_Data_Augmentation-portuguese

Automatic Speech Recognition
Transformers
PyTorch
Portuguese
wav2vec2
audio
speech
Portuguese-speech-corpus
PyTorch
Eval Results
Inference Endpoints
Model card Files Community
1
Edresson commited on
Commit
c70667d
•
1 Parent(s): b2f7d3d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -43,7 +43,7 @@ tokenizer = AutoTokenizer.from_pretrained("Edresson/wav2vec2-large-100k-voxpopul
43
  model = Wav2Vec2ForCTC.from_pretrained("Edresson/wav2vec2-large-100k-voxpopuli-ft-Common_Voice_plus_TTS-Dataset_plus_Data_Augmentation-portuguese")
44
  ```
45
  # Results
46
- For the results check the [article (Soon)]()
47
 
48
  # Example test with Common Voice Dataset
49
 
 
43
  model = Wav2Vec2ForCTC.from_pretrained("Edresson/wav2vec2-large-100k-voxpopuli-ft-Common_Voice_plus_TTS-Dataset_plus_Data_Augmentation-portuguese")
44
  ```
45
  # Results
46
+ For the results check the [paper](https://arxiv.org/abs/2204.00618)
47
 
48
  # Example test with Common Voice Dataset
49