Hugging Face's logo

sravan-gorugantu
/
model

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Inference Endpoints
Model card Files Metrics Community
sravan-gorugantu commited on
Commit
5da24e7
•
1 Parent(s): 9cf2568

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +68 -18
  2. model.safetensors +2 -2
  3. preprocessor_config.json +3 -7
  4. runs/Apr16_13-53-05_voice-ai-transformer/events.out.tfevents.1713275586.voice-ai-transformer.282817.3 +3 -0
  5. runs/Apr16_14-02-38_voice-ai-transformer/events.out.tfevents.1713276200.voice-ai-transformer.1004702.0 +3 -0
  6. runs/Apr19_07-35-44_voice-ai-transformer/events.out.tfevents.1713512150.voice-ai-transformer.1056517.0 +3 -0
  7. training_args.bin +1 -1
config.json CHANGED
@@ -1,37 +1,87 @@
1
  {
2
- "_name_or_path": "MIT/ast-finetuned-speech-commands-v2",
 
 
3
  "architectures": [
4
- "ASTForAudioClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "frequency_stride": 10,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.0,
 
10
  "hidden_size": 768,
11
  "id2label": {
12
  "0": "door_close",
13
  "1": "door_open",
14
- "2": "door_stop",
15
- "3": "unknown"
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
19
  "label2id": {
20
  "door_close": "0",
21
  "door_open": "1",
22
- "door_stop": "2",
23
- "unknown": "3"
24
  },
25
- "layer_norm_eps": 1e-12,
26
- "max_length": 128,
27
- "model_type": "audio-spectrogram-transformer",
 
 
 
 
 
 
28
  "num_attention_heads": 12,
 
 
 
29
  "num_hidden_layers": 12,
30
- "num_mel_bins": 128,
31
- "patch_size": 16,
32
- "problem_type": "single_label_classification",
33
- "qkv_bias": true,
34
- "time_stride": 10,
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.38.1"
 
 
37
  }
 
1
  {
2
+ "_name_or_path": "anton-l/hubert-base-ft-keyword-spotting",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
  "architectures": [
6
+ "HubertForSequenceClassification"
7
  ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_dropout": 0.0,
45
+ "feat_extract_norm": "group",
46
+ "feat_proj_dropout": 0.1,
47
+ "feat_proj_layer_norm": true,
48
+ "final_dropout": 0.1,
49
+ "finetuning_task": "audio-classification",
50
+ "gradient_checkpointing": false,
51
  "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_dropout_prob": 0.1,
54
  "hidden_size": 768,
55
  "id2label": {
56
  "0": "door_close",
57
  "1": "door_open",
58
+ "2": "unknown"
 
59
  },
60
  "initializer_range": 0.02,
61
  "intermediate_size": 3072,
62
  "label2id": {
63
  "door_close": "0",
64
  "door_open": "1",
65
+ "unknown": "2"
 
66
  },
67
+ "layer_norm_eps": 1e-05,
68
+ "layerdrop": 0.1,
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_prob": 0.05,
75
+ "model_type": "hubert",
76
  "num_attention_heads": 12,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
  "num_hidden_layers": 12,
81
+ "pad_token_id": 0,
82
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
 
 
83
  "torch_dtype": "float32",
84
+ "transformers_version": "4.38.1",
85
+ "use_weighted_layer_sum": false,
86
+ "vocab_size": 32
87
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:593b6740e5b51533a2203d7f0f137287066cdf69f482853a8ec6d0c7191f85cf
3
- size 341515296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12179fae31f67f0cdcf9b1aadfdce40db59f695b9e3559ce373641c5f53d0735
3
+ size 378302972
preprocessor_config.json CHANGED
@@ -1,13 +1,9 @@
1
  {
2
  "do_normalize": true,
3
- "feature_extractor_type": "ASTFeatureExtractor",
4
  "feature_size": 1,
5
- "max_length": 128,
6
- "mean": -6.845978,
7
- "num_mel_bins": 128,
8
  "padding_side": "right",
9
- "padding_value": 0.0,
10
  "return_attention_mask": false,
11
- "sampling_rate": 16000,
12
- "std": 5.5654526
13
  }
 
1
  {
2
  "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
 
 
 
5
  "padding_side": "right",
6
+ "padding_value": 0,
7
  "return_attention_mask": false,
8
+ "sampling_rate": 16000
 
9
  }
runs/Apr16_13-53-05_voice-ai-transformer/events.out.tfevents.1713275586.voice-ai-transformer.282817.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eac0e834f606055dac8b9e18a7043f1e662cf4176cf5d4826aff49031cef72a
3
+ size 4184
runs/Apr16_14-02-38_voice-ai-transformer/events.out.tfevents.1713276200.voice-ai-transformer.1004702.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c4a2c70fa1760ee12826b8ee3abb995cddabb55a8b3c944744cfa383c482d6
3
+ size 4184
runs/Apr19_07-35-44_voice-ai-transformer/events.out.tfevents.1713512150.voice-ai-transformer.1056517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669b489d83e233b0132b1559e6632484ecf4b07c3f1ef62f0c1baaced960abce
3
+ size 13581
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c8d5c2a980e85ed3f95fca41917e82993ba5d4d473791ec2a2ec3b023e01d06
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cd465e43cbd1a7d2b093d60b3605051a21bfdc8e4a1d3d5fa9b0a0642a5308
3
  size 4920