alvanlii
/

whisper-small-cantonese

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

alvanlii commited on Aug 2

Commit

cdaf4c3

•

1 Parent(s): 02e6492

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -77,7 +77,7 @@ processor = WhisperProcessor.from_pretrained(MODEL_NAME)
 model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME)
 model.config.forced_decoder_ids = None
-model.config.suppress_tokens = []
 model.config.use_cache = False
 processed_in = processor(y, sampling_rate=sr, return_tensors="pt")

 model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME)
 model.config.forced_decoder_ids = None
+model.config.suppress_tokens = None
 model.config.use_cache = False
 processed_in = processor(y, sampling_rate=sr, return_tensors="pt")