Hugging Face's logo

niobures
/
wav2vec2

ONNX
Model card Files
xet
Community
niobures commited on
Commit
3a22dee
·
verified ·
1 Parent(s): e755079

wav2vec2

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. AudioEmoDetect_v1_onnx/.gitattributes +35 -0
  2. AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.config +93 -0
  3. AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.feature +9 -0
  4. AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.onnx +3 -0
  5. AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.yaml +14 -0
  6. AudioEmoDetect_v1_onnx/source.txt +1 -0
  7. audio-emotion-detection-onnx/.gitattributes +35 -0
  8. audio-emotion-detection-onnx/README.md +3 -0
  9. audio-emotion-detection-onnx/config.json +133 -0
  10. audio-emotion-detection-onnx/onnx/model_quantized.onnx +3 -0
  11. audio-emotion-detection-onnx/preprocessor_config.json +10 -0
  12. audio-emotion-detection-onnx/source.txt +1 -0
  13. unispeech-sat-emotion-russian-resd_onnx/.gitattributes +35 -0
  14. unispeech-sat-emotion-russian-resd_onnx/source.txt +1 -0
  15. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.config +127 -0
  16. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.feature +9 -0
  17. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.onnx +3 -0
  18. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.processor +21 -0
  19. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.tokens +40 -0
  20. unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.yaml +15 -0
  21. urdu-audio-emotions_onnx/.gitattributes +35 -0
  22. urdu-audio-emotions_onnx/source.txt +1 -0
  23. urdu-audio-emotions_onnx/urdu-audio-emotions.config +129 -0
  24. urdu-audio-emotions_onnx/urdu-audio-emotions.feature +9 -0
  25. urdu-audio-emotions_onnx/urdu-audio-emotions.onnx +3 -0
  26. urdu-audio-emotions_onnx/urdu-audio-emotions.yaml +12 -0
  27. w2v2c_ko_emotion_onnx/.gitattributes +35 -0
  28. w2v2c_ko_emotion_onnx/source.txt +1 -0
  29. w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.config +124 -0
  30. w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.feature +9 -0
  31. w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.onnx +3 -0
  32. w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.yaml +12 -0
  33. wav2vec2-base-Speech_Emotion_Recognition_onnx/.gitattributes +35 -0
  34. wav2vec2-base-Speech_Emotion_Recognition_onnx/source.txt +1 -0
  35. wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.config +134 -0
  36. wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.feature +9 -0
  37. wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.onnx +3 -0
  38. wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.yaml +14 -0
  39. wav2vec2-base-finetuned-emodb_onnx/.gitattributes +35 -0
  40. wav2vec2-base-finetuned-emodb_onnx/source.txt +1 -0
  41. wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.config +132 -0
  42. wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.feature +9 -0
  43. wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.onnx +3 -0
  44. wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.yaml +13 -0
  45. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/.gitattributes +35 -0
  46. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/source.txt +1 -0
  47. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.config +134 -0
  48. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.feature +9 -0
  49. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.onnx +3 -0
  50. wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.yaml +14 -0
AudioEmoDetect_v1_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.config ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ HubertConfig {
2
+ "_name_or_path": "PrachiPatel/AudioEmoDetect_v1",
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
+ "gradient_checkpointing": false,
50
+ "hidden_act": "gelu",
51
+ "hidden_dropout": 0.1,
52
+ "hidden_dropout_prob": 0.1,
53
+ "hidden_size": 768,
54
+ "id2label": {
55
+ "0": "Anger",
56
+ "1": "Disgust",
57
+ "2": "Fear",
58
+ "3": "Happiness",
59
+ "4": "Neutral",
60
+ "5": "Sadness"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "LABEL_0": 0,
66
+ "LABEL_1": 1,
67
+ "LABEL_2": 2,
68
+ "LABEL_3": 3,
69
+ "LABEL_4": 4,
70
+ "LABEL_5": 5
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "hubert",
81
+ "num_attention_heads": 12,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 12,
86
+ "pad_token_id": 0,
87
+ "pooling_mode": "mean",
88
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
89
+ "torch_dtype": "float32",
90
+ "transformers_version": "4.41.1",
91
+ "use_weighted_layer_sum": false,
92
+ "vocab_size": 32
93
+ }
AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
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
+ }
AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b62b4b3e7290be70d72440cf70765005d675695243a03a5781ede4678c05111
3
+ size 378573700
AudioEmoDetect_v1_onnx/AudioEmoDetect_v1.yaml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: PrachiPatel/AudioEmoDetect_v1
3
+ labels:
4
+ 0: Anger
5
+ 1: Disgust
6
+ 2: Fear
7
+ 3: Happiness
8
+ 4: Neutral
9
+ 5: Sadness
10
+ model: HubertForSequenceClassification
11
+ sampling_rate: 16000
12
+ shape:
13
+ - 1
14
+ - 320000
AudioEmoDetect_v1_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/AudioEmoDetect_v1_onnx
audio-emotion-detection-onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
audio-emotion-detection-onnx/README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
audio-emotion-detection-onnx/config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Hatman/audio-emotion-detection",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": true,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "Angry",
61
+ "1": "Disgusted",
62
+ "2": "Fearful",
63
+ "3": "Happy",
64
+ "4": "Neutral",
65
+ "5": "Sad",
66
+ "6": "Suprised"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 4096,
70
+ "label2id": {
71
+ "Angry": "0",
72
+ "Disgusted": "1",
73
+ "Fearful": "2",
74
+ "Happy": "3",
75
+ "Neutral": "4",
76
+ "Sad": "5",
77
+ "Suprised": "6"
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "layerdrop": 0.05,
81
+ "mask_channel_length": 10,
82
+ "mask_channel_min_space": 1,
83
+ "mask_channel_other": 0.0,
84
+ "mask_channel_prob": 0.0,
85
+ "mask_channel_selection": "static",
86
+ "mask_feature_length": 10,
87
+ "mask_feature_min_masks": 0,
88
+ "mask_feature_prob": 0.0,
89
+ "mask_time_length": 10,
90
+ "mask_time_min_masks": 2,
91
+ "mask_time_min_space": 1,
92
+ "mask_time_other": 0.0,
93
+ "mask_time_prob": 0.05,
94
+ "mask_time_selection": "static",
95
+ "model_type": "wav2vec2",
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 16,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 24,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 1024,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 256,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "transformers_version": "4.37.2",
130
+ "use_weighted_layer_sum": false,
131
+ "vocab_size": 33,
132
+ "xvector_output_dim": 512
133
+ }
audio-emotion-detection-onnx/onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a04319bc2a171a948f23375fb2397c7f99c4fbd9a984325c0ad9082964d8b5
3
+ size 1263408071
audio-emotion-detection-onnx/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
audio-emotion-detection-onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/Aroganta/audio-emotion-detection-onnx
unispeech-sat-emotion-russian-resd_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
unispeech-sat-emotion-russian-resd_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/unispeech-sat-emotion-russian-resd_onnx
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.config ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ UniSpeechSatConfig {
2
+ "_name_or_path": "Aniemore/unispeech-sat-emotion-russian-resd",
3
+ "activation_dropout": 0.05,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "UniSpeechSatForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.05,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 768,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": false,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "sum",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.05,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.05,
52
+ "finetuning_task": [
53
+ "unispeech_sat_classification"
54
+ ],
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.05,
57
+ "hidden_size": 1024,
58
+ "id2label": {
59
+ "0": "anger",
60
+ "1": "disgust",
61
+ "2": "enthusiasm",
62
+ "3": "fear",
63
+ "4": "happiness",
64
+ "5": "neutral",
65
+ "6": "sadness"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 4096,
69
+ "label2id": {
70
+ "anger": 0,
71
+ "disgust": 1,
72
+ "enthusiasm": 2,
73
+ "fear": 3,
74
+ "happiness": 4,
75
+ "neutral": 5,
76
+ "sadness": 6
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.05,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "unispeech-sat",
87
+ "num_attention_heads": 16,
88
+ "num_clusters": 504,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 24,
95
+ "num_negatives": 100,
96
+ "pad_token_id": 0,
97
+ "pooling_mode": "mean",
98
+ "problem_type": "single_label_classification",
99
+ "proj_codevector_dim": 768,
100
+ "tdnn_dilation": [
101
+ 1,
102
+ 2,
103
+ 3,
104
+ 1,
105
+ 1
106
+ ],
107
+ "tdnn_dim": [
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 1500
113
+ ],
114
+ "tdnn_kernel": [
115
+ 5,
116
+ 3,
117
+ 3,
118
+ 1,
119
+ 1
120
+ ],
121
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.41.1",
124
+ "use_weighted_layer_sum": false,
125
+ "vocab_size": 40,
126
+ "xvector_output_dim": 512
127
+ }
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
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": true,
8
+ "sampling_rate": 16000
9
+ }
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52c43e1933d1be1f8c2e1e10c4cf63f3f66802453d1764b374f0bd9e2cc6e91
3
+ size 1265552756
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.processor ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Processor:
2
+ - feature_extractor: Wav2Vec2FeatureExtractor {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
11
+
12
+ - tokenizer: Wav2Vec2CTCTokenizer(name_or_path='Aniemore/unispeech-sat-emotion-russian-resd', vocab_size=40, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True), added_tokens_decoder={
13
+ 0: AddedToken("<pad>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
14
+ 1: AddedToken("<s>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
15
+ 2: AddedToken("</s>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
16
+ 3: AddedToken("<unk>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
17
+ }
18
+
19
+ {
20
+ "processor_class": "Wav2Vec2Processor"
21
+ }
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.tokens ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 0: <pad>
2
+ 1: <s>
3
+ 2: </s>
4
+ 3: <unk>
5
+ 4: '|'
6
+ 5: ''''
7
+ 6: '-'
8
+ 7: а
9
+ 8: б
10
+ 9: в
11
+ 10: г
12
+ 11: д
13
+ 12: е
14
+ 13: ж
15
+ 14: з
16
+ 15: и
17
+ 16: й
18
+ 17: к
19
+ 18: л
20
+ 19: м
21
+ 20: н
22
+ 21: о
23
+ 22: п
24
+ 23: р
25
+ 24: с
26
+ 25: т
27
+ 26: у
28
+ 27: ф
29
+ 28: х
30
+ 29: ц
31
+ 30: ч
32
+ 31: ш
33
+ 32: щ
34
+ 33: ъ
35
+ 34: ы
36
+ 35: ь
37
+ 36: э
38
+ 37: ю
39
+ 38: я
40
+ 39: ё
unispeech-sat-emotion-russian-resd_onnx/unispeech-sat-emotion-russian-resd.yaml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: Aniemore/unispeech-sat-emotion-russian-resd
3
+ labels:
4
+ 0: anger
5
+ 1: disgust
6
+ 2: enthusiasm
7
+ 3: fear
8
+ 4: happiness
9
+ 5: neutral
10
+ 6: sadness
11
+ model: UniSpeechSatForSequenceClassification
12
+ sampling_rate: 16000
13
+ shape:
14
+ - 1
15
+ - 320000
urdu-audio-emotions_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
urdu-audio-emotions_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/urdu-audio-emotions_onnx
urdu-audio-emotions_onnx/urdu-audio-emotions.config ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Config {
2
+ "_name_or_path": "Talha/urdu-audio-emotions",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "Angry",
62
+ "1": "Happy",
63
+ "2": "Neutral",
64
+ "3": "Sad"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "Angry": "0",
70
+ "Happy": "1",
71
+ "Neutral": "2",
72
+ "Sad": "3"
73
+ },
74
+ "layer_norm_eps": 1e-05,
75
+ "layerdrop": 0.1,
76
+ "mask_channel_length": 10,
77
+ "mask_channel_min_space": 1,
78
+ "mask_channel_other": 0.0,
79
+ "mask_channel_prob": 0.0,
80
+ "mask_channel_selection": "static",
81
+ "mask_feature_length": 10,
82
+ "mask_feature_min_masks": 0,
83
+ "mask_feature_prob": 0.0,
84
+ "mask_time_length": 10,
85
+ "mask_time_min_masks": 2,
86
+ "mask_time_min_space": 1,
87
+ "mask_time_other": 0.0,
88
+ "mask_time_prob": 0.075,
89
+ "mask_time_selection": "static",
90
+ "model_type": "wav2vec2",
91
+ "num_adapter_layers": 3,
92
+ "num_attention_heads": 16,
93
+ "num_codevector_groups": 2,
94
+ "num_codevectors_per_group": 320,
95
+ "num_conv_pos_embedding_groups": 16,
96
+ "num_conv_pos_embeddings": 128,
97
+ "num_feat_extract_layers": 7,
98
+ "num_hidden_layers": 24,
99
+ "num_negatives": 100,
100
+ "output_hidden_size": 1024,
101
+ "pad_token_id": 0,
102
+ "proj_codevector_dim": 768,
103
+ "tdnn_dilation": [
104
+ 1,
105
+ 2,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "tdnn_dim": [
111
+ 512,
112
+ 512,
113
+ 512,
114
+ 512,
115
+ 1500
116
+ ],
117
+ "tdnn_kernel": [
118
+ 5,
119
+ 3,
120
+ 3,
121
+ 1,
122
+ 1
123
+ ],
124
+ "torch_dtype": "float32",
125
+ "transformers_version": "4.41.1",
126
+ "use_weighted_layer_sum": false,
127
+ "vocab_size": 32,
128
+ "xvector_output_dim": 512
129
+ }
urdu-audio-emotions_onnx/urdu-audio-emotions.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
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": true,
8
+ "sampling_rate": 16000
9
+ }
urdu-audio-emotions_onnx/urdu-audio-emotions.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7623de49f735de6bd611721738c495575192efa1bd4ac04bf8409d0e9a78d2d5
3
+ size 1263404950
urdu-audio-emotions_onnx/urdu-audio-emotions.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: Talha/urdu-audio-emotions
3
+ labels:
4
+ 0: Angry
5
+ 1: Happy
6
+ 2: Neutral
7
+ 3: Sad
8
+ model: Wav2Vec2ForSequenceClassification
9
+ sampling_rate: 16000
10
+ shape:
11
+ - 1
12
+ - 320000
w2v2c_ko_emotion_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
w2v2c_ko_emotion_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/w2v2c_ko_emotion_onnx
w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.config ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2ConformerConfig {
2
+ "_name_or_path": "JUNGWJ/w2v2c_ko_emotion",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ConformerForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "conformer_conv_dropout": 0.1,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "conv_dim": [
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512
27
+ ],
28
+ "conv_kernel": [
29
+ 10,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 2,
35
+ 2
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2
45
+ ],
46
+ "ctc_loss_reduction": "mean",
47
+ "ctc_zero_infinity": true,
48
+ "diversity_loss_weight": 0.1,
49
+ "do_stable_layer_norm": true,
50
+ "eos_token_id": 2,
51
+ "feat_extract_activation": "gelu",
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Happy",
62
+ "1": "Sad",
63
+ "2": "Angry",
64
+ "3": "Anxious"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "Angry": "2",
70
+ "Anxious": "3",
71
+ "Happy": "0",
72
+ "Sad": "1"
73
+ },
74
+ "layer_norm_eps": 1e-05,
75
+ "layerdrop": 0.0,
76
+ "mask_feature_length": 64,
77
+ "mask_feature_min_masks": 0,
78
+ "mask_feature_prob": 0.05,
79
+ "mask_time_length": 10,
80
+ "mask_time_min_masks": 2,
81
+ "mask_time_prob": 0.05,
82
+ "max_source_positions": 5000,
83
+ "model_type": "wav2vec2-conformer",
84
+ "num_adapter_layers": 3,
85
+ "num_attention_heads": 12,
86
+ "num_codevector_groups": 2,
87
+ "num_codevectors_per_group": 320,
88
+ "num_conv_pos_embedding_groups": 16,
89
+ "num_conv_pos_embeddings": 128,
90
+ "num_feat_extract_layers": 7,
91
+ "num_hidden_layers": 12,
92
+ "num_negatives": 100,
93
+ "output_hidden_size": 768,
94
+ "pad_token_id": 0,
95
+ "position_embeddings_type": "relative",
96
+ "proj_codevector_dim": 256,
97
+ "rotary_embedding_base": 10000,
98
+ "tdnn_dilation": [
99
+ 1,
100
+ 2,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "tdnn_dim": [
106
+ 512,
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 1500
111
+ ],
112
+ "tdnn_kernel": [
113
+ 5,
114
+ 3,
115
+ 3,
116
+ 1,
117
+ 1
118
+ ],
119
+ "torch_dtype": "float32",
120
+ "transformers_version": "4.41.1",
121
+ "use_weighted_layer_sum": false,
122
+ "vocab_size": 111,
123
+ "xvector_output_dim": 512
124
+ }
w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
2
+ "do_normalize": true,
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
+ }
w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e094a84c8c33b9dd3d9b7d8e8a83d42e30b2ae9fe51bc682ce33a12b20ab663b
3
+ size 732226369
w2v2c_ko_emotion_onnx/w2v2c_ko_emotion.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: JUNGWJ/w2v2c_ko_emotion
3
+ labels:
4
+ 0: Happy
5
+ 1: Sad
6
+ 2: Angry
7
+ 3: Anxious
8
+ model: Wav2Vec2ConformerForSequenceClassification
9
+ sampling_rate: 16000
10
+ shape:
11
+ - 1
12
+ - 320000
wav2vec2-base-Speech_Emotion_Recognition_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
wav2vec2-base-Speech_Emotion_Recognition_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ wav2vec2-base-Speech_Emotion_Recognition_onnx
wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.config ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Config {
2
+ "_name_or_path": "DunnBC22/wav2vec2-base-Speech_Emotion_Recognition",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "SAD",
61
+ "1": "ANGRY",
62
+ "2": "DISGUST",
63
+ "3": "FEAR",
64
+ "4": "HAPPY",
65
+ "5": "NEUTRAL"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 3072,
69
+ "label2id": {
70
+ "ANGRY": "1",
71
+ "DISGUST": "2",
72
+ "FEAR": "3",
73
+ "HAPPY": "4",
74
+ "NEUTRAL": "5",
75
+ "SAD": "0"
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "layerdrop": 0.0,
79
+ "mask_channel_length": 10,
80
+ "mask_channel_min_space": 1,
81
+ "mask_channel_other": 0.0,
82
+ "mask_channel_prob": 0.0,
83
+ "mask_channel_selection": "static",
84
+ "mask_feature_length": 10,
85
+ "mask_feature_min_masks": 0,
86
+ "mask_feature_prob": 0.0,
87
+ "mask_time_length": 10,
88
+ "mask_time_min_masks": 2,
89
+ "mask_time_min_space": 1,
90
+ "mask_time_other": 0.0,
91
+ "mask_time_prob": 0.05,
92
+ "mask_time_selection": "static",
93
+ "model_type": "wav2vec2",
94
+ "no_mask_channel_overlap": false,
95
+ "no_mask_time_overlap": false,
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 12,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 12,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 768,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 256,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.41.1",
131
+ "use_weighted_layer_sum": false,
132
+ "vocab_size": 32,
133
+ "xvector_output_dim": 512
134
+ }
wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b11485a7a5bf84f0cf74b116f1d94bccbc2181a30dd7f86c8ce44d2f38d612f
3
+ size 378583063
wav2vec2-base-Speech_Emotion_Recognition_onnx/wav2vec2-base-Speech_Emotion_Recognition.yaml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: DunnBC22/wav2vec2-base-Speech_Emotion_Recognition
3
+ labels:
4
+ 0: SAD
5
+ 1: ANGRY
6
+ 2: DISGUST
7
+ 3: FEAR
8
+ 4: HAPPY
9
+ 5: NEUTRAL
10
+ model: Wav2Vec2ForSequenceClassification
11
+ sampling_rate: 16000
12
+ shape:
13
+ - 1
14
+ - 320000
wav2vec2-base-finetuned-emodb_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
wav2vec2-base-finetuned-emodb_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/wav2vec2-base-finetuned-emodb_onnx
wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.config ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Config {
2
+ "_name_or_path": "Hamzaaa/wav2vec2-base-finetuned-emodb",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "anger",
61
+ "1": "disgust",
62
+ "2": "fear",
63
+ "3": "happiness",
64
+ "4": "sadness"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "anger": 0,
70
+ "disgust": 1,
71
+ "fear": 2,
72
+ "happiness": 3,
73
+ "sadness": 4
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.0,
77
+ "mask_channel_length": 10,
78
+ "mask_channel_min_space": 1,
79
+ "mask_channel_other": 0.0,
80
+ "mask_channel_prob": 0.0,
81
+ "mask_channel_selection": "static",
82
+ "mask_feature_length": 10,
83
+ "mask_feature_min_masks": 0,
84
+ "mask_feature_prob": 0.0,
85
+ "mask_time_length": 10,
86
+ "mask_time_min_masks": 2,
87
+ "mask_time_min_space": 1,
88
+ "mask_time_other": 0.0,
89
+ "mask_time_prob": 0.05,
90
+ "mask_time_selection": "static",
91
+ "model_type": "wav2vec2",
92
+ "no_mask_channel_overlap": false,
93
+ "no_mask_time_overlap": false,
94
+ "num_adapter_layers": 3,
95
+ "num_attention_heads": 12,
96
+ "num_codevector_groups": 2,
97
+ "num_codevectors_per_group": 320,
98
+ "num_conv_pos_embedding_groups": 16,
99
+ "num_conv_pos_embeddings": 128,
100
+ "num_feat_extract_layers": 7,
101
+ "num_hidden_layers": 12,
102
+ "num_negatives": 100,
103
+ "output_hidden_size": 768,
104
+ "pad_token_id": 0,
105
+ "proj_codevector_dim": 256,
106
+ "tdnn_dilation": [
107
+ 1,
108
+ 2,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "tdnn_dim": [
114
+ 512,
115
+ 512,
116
+ 512,
117
+ 512,
118
+ 1500
119
+ ],
120
+ "tdnn_kernel": [
121
+ 5,
122
+ 3,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
+ "torch_dtype": "float32",
128
+ "transformers_version": "4.41.1",
129
+ "use_weighted_layer_sum": false,
130
+ "vocab_size": 32,
131
+ "xvector_output_dim": 512
132
+ }
wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc008450e379642afc3197dbc7c2a19fb614e43e9f45527bed2a3e99d782d18
3
+ size 378582035
wav2vec2-base-finetuned-emodb_onnx/wav2vec2-base-finetuned-emodb.yaml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: Hamzaaa/wav2vec2-base-finetuned-emodb
3
+ labels:
4
+ 0: anger
5
+ 1: disgust
6
+ 2: fear
7
+ 3: happiness
8
+ 4: sadness
9
+ model: Wav2Vec2ForSequenceClassification
10
+ sampling_rate: 16000
11
+ shape:
12
+ - 1
13
+ - 320000
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/steveway/wav2vec2-base-finetuned-sentiment-mesd-v9_onnx
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.config ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Config {
2
+ "_name_or_path": "DrishtiSharma/wav2vec2-base-finetuned-sentiment-mesd-v9",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "Anger",
61
+ "1": "Disgust",
62
+ "2": "Fear",
63
+ "3": "Happiness",
64
+ "4": "Neutral",
65
+ "5": "Sadness"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 3072,
69
+ "label2id": {
70
+ "Anger": "0",
71
+ "Disgust": "1",
72
+ "Fear": "2",
73
+ "Happiness": "3",
74
+ "Neutral": "4",
75
+ "Sadness": "5"
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "layerdrop": 0.0,
79
+ "mask_channel_length": 10,
80
+ "mask_channel_min_space": 1,
81
+ "mask_channel_other": 0.0,
82
+ "mask_channel_prob": 0.0,
83
+ "mask_channel_selection": "static",
84
+ "mask_feature_length": 10,
85
+ "mask_feature_min_masks": 0,
86
+ "mask_feature_prob": 0.0,
87
+ "mask_time_length": 10,
88
+ "mask_time_min_masks": 2,
89
+ "mask_time_min_space": 1,
90
+ "mask_time_other": 0.0,
91
+ "mask_time_prob": 0.05,
92
+ "mask_time_selection": "static",
93
+ "model_type": "wav2vec2",
94
+ "no_mask_channel_overlap": false,
95
+ "no_mask_time_overlap": false,
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 12,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 12,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 768,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 256,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.41.1",
131
+ "use_weighted_layer_sum": false,
132
+ "vocab_size": 32,
133
+ "xvector_output_dim": 512
134
+ }
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15aadf5ccc0418390fdee951caad43430e2adf6256b7f57b2c5eb0e515421efd
3
+ size 378583063
wav2vec2-base-finetuned-sentiment-mesd-v9_onnx/wav2vec2-base-finetuned-sentiment-mesd-v9.yaml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ full_name: DrishtiSharma/wav2vec2-base-finetuned-sentiment-mesd-v9
3
+ labels:
4
+ 0: Anger
5
+ 1: Disgust
6
+ 2: Fear
7
+ 3: Happiness
8
+ 4: Neutral
9
+ 5: Sadness
10
+ model: Wav2Vec2ForSequenceClassification
11
+ sampling_rate: 16000
12
+ shape:
13
+ - 1
14
+ - 320000