Hugging Face's logo

microsoft
/
unispeech-sat-large-sd

Transformers
PyTorch
English
unispeech-sat
audio-frame-classification
speech
Inference Endpoints
Model card Files Community
1
speech-test commited on
Commit
d505b49
•
1 Parent(s): 5311d32

Upload

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. preprocessor_config.json +1 -1
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -97,8 +97,8 @@
97
  ],
98
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
  "torch_dtype": "float32",
100
- "transformers_version": "4.14.0.dev0",
101
- "use_weighted_layer_sum": false,
102
  "vocab_size": 256,
103
  "xvector_output_dim": 512
104
  }
 
97
  ],
98
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
  "torch_dtype": "float32",
100
+ "transformers_version": "4.15.0.dev0",
101
+ "use_weighted_layer_sum": true,
102
  "vocab_size": 256,
103
  "xvector_output_dim": 512
104
  }
preprocessor_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "do_normalize": false,
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
 
1
  {
2
+ "do_normalize": true,
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f8b71779d0a5ed68f414d8c0d7231309a47a0e1b3dca2a41cdf70e30712d730
3
- size 1261929905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fe3528209a648ef00744865efae70b470f47efdefbce0152ea3065b3aa6b85
3
+ size 1261930351