Hugging Face's logo

infinitejoy
/
wav2vec2-large-xls-r-300m-hindi

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Hindi
wav2vec2
generated_from_trainer
hf-asr-leaderboard
model_for_talk
mozilla-foundation/common_voice_7_0
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Metrics Community
infinitejoy commited on
Commit
55be747
•
1 Parent(s): 389c46d

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. config.json +6 -7
  2. preprocessor_config.json +1 -1
  3. pytorch_model.bin +2 -2
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
- "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
6
  "add_adapter": false,
@@ -52,7 +52,6 @@
52
  "feat_proj_dropout": 0.0,
53
  "feat_quantizer_dropout": 0.0,
54
  "final_dropout": 0.0,
55
- "gradient_checkpointing": false,
56
  "hidden_act": "gelu",
57
  "hidden_dropout": 0.0,
58
  "hidden_size": 1024,
@@ -60,12 +59,12 @@
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 +76,7 @@
77
  "num_hidden_layers": 24,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1024,
80
- "pad_token_id": 70,
81
  "proj_codevector_dim": 768,
82
  "tdnn_dilation": [
83
  1,
@@ -103,6 +102,6 @@
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.16.0.dev0",
105
  "use_weighted_layer_sum": false,
106
- "vocab_size": 73,
107
  "xvector_output_dim": 512
108
  }
1
  {
2
  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
6
  "add_adapter": false,
52
  "feat_proj_dropout": 0.0,
53
  "feat_quantizer_dropout": 0.0,
54
  "final_dropout": 0.0,
 
55
  "hidden_act": "gelu",
56
  "hidden_dropout": 0.0,
57
  "hidden_size": 1024,
59
  "intermediate_size": 4096,
60
  "layer_norm_eps": 1e-05,
61
  "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
  "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
  "mask_time_length": 10,
66
  "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
  "model_type": "wav2vec2",
69
  "num_adapter_layers": 3,
70
  "num_attention_heads": 16,
76
  "num_hidden_layers": 24,
77
  "num_negatives": 100,
78
  "output_hidden_size": 1024,
79
+ "pad_token_id": 94,
80
  "proj_codevector_dim": 768,
81
  "tdnn_dilation": [
82
  1,
102
  "torch_dtype": "float32",
103
  "transformers_version": "4.16.0.dev0",
104
  "use_weighted_layer_sum": false,
105
+ "vocab_size": 96,
106
  "xvector_output_dim": 512
107
  }
preprocessor_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
6
- "padding_value": 0.0,
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
6
+ "padding_value": 0,
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47682c1f678b8697f4d9536b813c073b8a3e09df1fe54bc7b631f7b20362c3f7
3
- size 1262222961
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560a64115d3b59fd7c95a561f879a235aceeb50270cb3cb4d730209c418a074b
3
+ size 1262317297
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ddca6ab6577943dd1fcf0e064f2418cd1f09124c5d54208b7b8bd81bf61bb99
3
  size 3055
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7e4c1247dd1baef6502ff7bc2a5dce9a95197cece15b3478a36d82911732bf
3
  size 3055