Hugging Face's logo

vitouphy
/
wav2vec2-xls-r-300m-khmer

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Khmer
wav2vec2
openslr
robust-speech-event
Generated from Trainer
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Community
2
vitouphy commited on
Commit
a33a424
·
1 Parent(s): 93a566f

add model

Browse files
Files changed (2) hide show
  1. config.json +6 -6
  2. pytorch_model.bin +1 -1
config.json CHANGED
@@ -8,7 +8,7 @@
8
  "architectures": [
9
  "Wav2Vec2ForCTC"
10
  ],
11
- "attention_dropout": 0.0,
12
  "bos_token_id": 1,
13
  "classifier_proj_size": 256,
14
  "codevector_dim": 768,
@@ -54,18 +54,18 @@
54
  "final_dropout": 0.0,
55
  "gradient_checkpointing": false,
56
  "hidden_act": "gelu",
57
- "hidden_dropout": 0.0,
58
  "hidden_size": 1024,
59
  "initializer_range": 0.02,
60
  "intermediate_size": 4096,
61
  "layer_norm_eps": 1e-05,
62
  "layerdrop": 0.0,
63
- "mask_feature_length": 10,
64
  "mask_feature_min_masks": 0,
65
- "mask_feature_prob": 0.0,
66
  "mask_time_length": 10,
67
  "mask_time_min_masks": 2,
68
- "mask_time_prob": 0.05,
69
  "model_type": "wav2vec2",
70
  "num_adapter_layers": 3,
71
  "num_attention_heads": 16,
@@ -77,7 +77,7 @@
77
  "num_hidden_layers": 24,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1024,
80
- "pad_token_id": 73,
81
  "proj_codevector_dim": 768,
82
  "tdnn_dilation": [
83
  1,
 
8
  "architectures": [
9
  "Wav2Vec2ForCTC"
10
  ],
11
+ "attention_dropout": 0.1,
12
  "bos_token_id": 1,
13
  "classifier_proj_size": 256,
14
  "codevector_dim": 768,
 
54
  "final_dropout": 0.0,
55
  "gradient_checkpointing": false,
56
  "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
  "hidden_size": 1024,
59
  "initializer_range": 0.02,
60
  "intermediate_size": 4096,
61
  "layer_norm_eps": 1e-05,
62
  "layerdrop": 0.0,
63
+ "mask_feature_length": 64,
64
  "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.25,
66
  "mask_time_length": 10,
67
  "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.75,
69
  "model_type": "wav2vec2",
70
  "num_adapter_layers": 3,
71
  "num_attention_heads": 16,
 
77
  "num_hidden_layers": 24,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1024,
80
+ "pad_token_id": 72,
81
  "proj_codevector_dim": 768,
82
  "tdnn_dilation": [
83
  1,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de338e5c1afe8724c486f34b78be6997d34259229acda73ba51b26c8c304a4d7
3
  size 1262231153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ba956e9839aa07016519fdfa526ee53a8b6a22d5f2e4b17268e9859f128846
3
  size 1262231153