facebook
/
wav2vec2-base-960h
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Patrick von Platen 2022-02-01 21:32:34 +00:00 committed by huggingface-web
parent 7717449af4
commit 5e3d456ec1
1 changed files with 1 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -44,19 +44,12 @@ To transcribe audio files the model can be used as a standalone acoustic model a
# load model and tokenizer # load model and tokenizer
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h") model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
# define function to read in sound file
def map_to_array(batch):
speech, _ = sf.read(batch["file"])
batch["speech"] = speech
return batch
# load dummy dataset and read soundfiles # load dummy dataset and read soundfiles
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation") ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
ds = ds.map(map_to_array)
# tokenize # tokenize
input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values # Batch size 1 input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values # Batch size 1
# retrieve logits # retrieve logits
logits = model(input_values).logits logits = model(input_values).logits