manandey
/

wav2vec2-large-xlsr-breton

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

manandey commited on Mar 26, 2021

Commit

dcfc6f9

•

1 Parent(s): 6d2f5ec

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ model-index:
          value: 54.04
 ---
-# Wav2Vec2-Large-XLSR-53-Irish
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Breton using the [Common Voice](https://huggingface.co/datasets/common_voice)
 When using this model, make sure that your speech input is sampled at 16kHz.
@@ -85,7 +85,7 @@ processor = Wav2Vec2Processor.from_pretrained("manandey/wav2vec2-large-xlsr-bret
 model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-breton")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\’\–\(\)\/\«\»\½\…]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.

          value: 54.04
 ---
+# Wav2Vec2-Large-XLSR-53-Breton
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Breton using the [Common Voice](https://huggingface.co/datasets/common_voice)
 When using this model, make sure that your speech input is sampled at 16kHz.
 model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-breton")
 model.to("cuda")
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\’\\–\\(\\)\\/\\«\\»\\½\\…]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.