patrickvonplaten
/

wav2vec2-large-960h-lv60-self-4-gram

Automatic Speech Recognition

hf-asr-leaderboard

Inference Endpoints

Model card Files Files and versions Community

patrickvonplaten commited on Apr 12, 2022

Commit

f7e2aa3

•

1 Parent(s): 8bc572b

up

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ model-index:
       value: 1.9
 ---
-# Wav2Vec2-Large-960h-Lv60 + Self-Training
 [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
@@ -106,4 +106,4 @@ print("WER:", wer(result["text"], result["transcription"]))
 | "clean" | "other" |
 |---|---|
-| 1.9 | 3.9 |

       value: 1.9
 ---
+# Wav2Vec2-Large-960h-Lv60 + Self-Training + 4-gram
 [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
 | "clean" | "other" |
 |---|---|
+| 1.9 | 3.9 |