washeed
/

Tag-lish_Audio_Transcriber

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

washeed commited on Apr 11

Commit

ebbe255

•

1 Parent(s): 8f730d7

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -39,7 +39,7 @@
   "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 32,
-  "num_mel_bins": 80,
   "pad_token_id": 50256,
   "scale_embedding": false,
   "torch_dtype": "float32",

   "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 32,
+  "num_mel_bins": 128,
   "pad_token_id": 50256,
   "scale_embedding": false,
   "torch_dtype": "float32",