Hugging Face's logo

facebook
/
wav2vec2-xls-r-300m

Transformers
PyTorch
wav2vec2
pretraining
speech
xls_r
xls_r_pretrained
Inference Endpoints
Model card Files Community
4
patrickvonplaten commited on
Commit
dfeb77c
•
1 Parent(s): 20eccef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -15,11 +15,13 @@ license: apache-2.0
15
 
16
  ![model image](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/xls_r.png)
17
 
 
 
18
  XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz.
19
 
20
  **Note**: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out [**this blog**](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) for more information about ASR.
21
 
22
- [XLS-R Paper](https://arxiv.org/abs/)
23
 
24
  Authors: Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli
25
 
 
15
 
16
  ![model image](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/xls_r.png)
17
 
18
+ [Facebook's Wav2Vec2 XLS-R](https://ai.facebook.com/blog/xls-r-self-supervised-speech-processing-for-128-languages) counting **2 billion** parameters.
19
+
20
  XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz.
21
 
22
  **Note**: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out [**this blog**](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) for more information about ASR.
23
 
24
+ [XLS-R Paper](https://arxiv.org/abs/2111.09296)
25
 
26
  Authors: Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli
27