jonatasgrosman
/

wav2vec2-large-xlsr-53-english

Automatic Speech Recognition Transformers PyTorch JAX Safetensors

English wav2vec2 audio hf-asr-leaderboard mozilla-foundation/common_voice_6_0 robust-speech-event speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

jonatasgrosman commited on Feb 22, 2022

Commit

62592d7

•

1 Parent(s): a35ec72

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice pt
       type: common_voice
       args: en
     metrics:
@@ -73,15 +73,15 @@ The script used for training can be found here: https://github.com/jonatasgrosma
 The model can be used directly (without a language model) as follows...
-Using the [ASRecognition](https://github.com/jonatasgrosman/asrecognition) library:
 ```python
-from asrecognition import ASREngine
-asr = ASREngine("en", model_path="jonatasgrosman/wav2vec2-large-xlsr-53-english")
 audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
-transcriptions = asr.transcribe(audio_paths)
 ```
 Writing your own inference script:

       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
+      name: Common Voice en
       type: common_voice
       args: en
     metrics:
 The model can be used directly (without a language model) as follows...
+Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
 ```python
+from huggingsound import SpeechRecognitionModel
+model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english")
 audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
+transcriptions = model.transcribe(audio_paths)
 ```
 Writing your own inference script: