Splend1dchan
/

wav2vec2-large-10min-lv60-self

Automatic Speech Recognition

hf-asr-leaderboard

Inference Endpoints

Model card Files Files and versions Community

Splend1dchan commited on May 30, 2022

Commit

287652e

•

1 Parent(s): a4f73be

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ model-index:
       value: None
 ---
 # Wav2Vec2-Large-10min-Lv60 + Self-Training
 [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
 The large model pretrained and fine-tuned on 10min of Libri-Light and Librispeech on 16kHz sampled speech audio. Model was trained with [Self-Training objective](https://arxiv.org/abs/2010.11430). When using the model make sure that your speech input is also sampled at 16Khz.

       value: None
 ---
 # Wav2Vec2-Large-10min-Lv60 + Self-Training
+# This is a direct state_dict transfer from fairseq to huggingface, the weights are identical
 [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
 The large model pretrained and fine-tuned on 10min of Libri-Light and Librispeech on 16kHz sampled speech audio. Model was trained with [Self-Training objective](https://arxiv.org/abs/2010.11430). When using the model make sure that your speech input is also sampled at 16Khz.