birgermoell
/

wav2vec2-large-xlsr-hungarian

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

patrickvonplaten commited on Mar 22, 2021

Commit

fb11f42

·

1 Parent(s): 755752a

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -41,8 +41,8 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 test_dataset = load_dataset("common_voice", "hu", split="test[:2%]").
-processor = Wav2Vec2Processor.from_pretrained("marma/wav2vec2-large-xlsr-swedish")
-model = Wav2Vec2ForCTC.from_pretrained("marma/wav2vec2-large-xlsr-swedish")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)

 test_dataset = load_dataset("common_voice", "hu", split="test[:2%]").
+processor = Wav2Vec2Processor.from_pretrained("birgermoell/wav2vec2-large-xlsr-hungarian")
+model = Wav2Vec2ForCTC.from_pretrained("birgermoell/wav2vec2-large-xlsr-hungarian")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)