Hugging Face's logo

megathil
/
fluency_prediction

Audio Classification
Transformers
Safetensors
whisper
Model card Files
xet
Community
megathil commited on
Commit
daf051e
·
verified ·
1 Parent(s): 1538237

Upload 5 files

Browse files
Files changed (5) hide show
  1. .gitattributes +35 -35
  2. config.json +166 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +14 -0
  5. training_args.bin +3 -0
.gitattributes CHANGED
@@ -1,35 +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
 
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
config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "megathil/fluency_prediction",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForAudioClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "id2label": {
43
+ "0": "Very Influent",
44
+ "1": "Influent",
45
+ "2": "Average",
46
+ "3": "Fluent"
47
+ },
48
+ "init_std": 0.02,
49
+ "is_encoder_decoder": true,
50
+ "label2id": {
51
+ "Average": "2",
52
+ "Fluent": "3",
53
+ "Influent": "1",
54
+ "Very Influent": "0"
55
+ },
56
+ "mask_feature_length": 10,
57
+ "mask_feature_min_masks": 0,
58
+ "mask_feature_prob": 0.0,
59
+ "mask_time_length": 10,
60
+ "mask_time_min_masks": 2,
61
+ "mask_time_prob": 0.05,
62
+ "max_length": 448,
63
+ "max_source_positions": 1500,
64
+ "max_target_positions": 448,
65
+ "median_filter_width": 7,
66
+ "model_type": "whisper",
67
+ "num_hidden_layers": 6,
68
+ "num_mel_bins": 80,
69
+ "pad_token_id": 50257,
70
+ "scale_embedding": false,
71
+ "suppress_tokens": [
72
+ 1,
73
+ 2,
74
+ 7,
75
+ 8,
76
+ 9,
77
+ 10,
78
+ 14,
79
+ 25,
80
+ 26,
81
+ 27,
82
+ 28,
83
+ 29,
84
+ 31,
85
+ 58,
86
+ 59,
87
+ 60,
88
+ 61,
89
+ 62,
90
+ 63,
91
+ 90,
92
+ 91,
93
+ 92,
94
+ 93,
95
+ 359,
96
+ 503,
97
+ 522,
98
+ 542,
99
+ 873,
100
+ 893,
101
+ 902,
102
+ 918,
103
+ 922,
104
+ 931,
105
+ 1350,
106
+ 1853,
107
+ 1982,
108
+ 2460,
109
+ 2627,
110
+ 3246,
111
+ 3253,
112
+ 3268,
113
+ 3536,
114
+ 3846,
115
+ 3961,
116
+ 4183,
117
+ 4667,
118
+ 6585,
119
+ 6647,
120
+ 7273,
121
+ 9061,
122
+ 9383,
123
+ 10428,
124
+ 10929,
125
+ 11938,
126
+ 12033,
127
+ 12331,
128
+ 12562,
129
+ 13793,
130
+ 14157,
131
+ 14635,
132
+ 15265,
133
+ 15618,
134
+ 16553,
135
+ 16604,
136
+ 18362,
137
+ 18956,
138
+ 20075,
139
+ 21675,
140
+ 22520,
141
+ 26130,
142
+ 26161,
143
+ 26435,
144
+ 28279,
145
+ 29464,
146
+ 31650,
147
+ 32302,
148
+ 32470,
149
+ 36865,
150
+ 42863,
151
+ 47425,
152
+ 49870,
153
+ 50254,
154
+ 50258,
155
+ 50358,
156
+ 50359,
157
+ 50360,
158
+ 50361,
159
+ 50362
160
+ ],
161
+ "torch_dtype": "float32",
162
+ "transformers_version": "4.38.2",
163
+ "use_cache": true,
164
+ "use_weighted_layer_sum": false,
165
+ "vocab_size": 51865
166
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c88669f07b8b236138a083860903062a3888830b56060000c09cec0a20d222
3
+ size 82902328
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d634f42ba0217ec57d987627ab09d38bda6606dd7b3920f7cb772dfaca25415a
3
+ size 4920