Hugging Face's logo

phonsobon
/
PsarAI-ASR-1B

Automatic Speech Recognition
Transformers
ONNX
Safetensors
Khmer
English
wav2vec2
speech
khmer
code-switching
mms
ctc
Eval Results (legacy)
Model card Files
xet
 Community
phonsobon commited on
Commit
b72f80b
·
verified ·
1 Parent(s): 8b7cec1

Upload onnx-int8

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. onnx/int8/config.json +108 -0
  3. onnx/int8/model.onnx +3 -0
  4. onnx/int8/model.onnx.data +3 -0
  5. onnx/int8/processor_config.json +12 -0
  6. onnx/int8/tokenizer_config.json +56 -0
  7. onnx/int8/vocab.json +155 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
36
+ onnx/int8/model.onnx.data filter=lfs diff=lfs merge=lfs -text
onnx/int8/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.05,
3
+ "adapter_attn_dim": 16,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.05,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 1024,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float16",
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": 0.05,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.05,
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,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 1024,
82
+ "target_lang": null,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "transformers_version": "5.20.2",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 153,
107
+ "xvector_output_dim": 512
108
+ }
onnx/int8/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ffcb53c10ef0c60cb1fd10257542ede06cb97473ee1d2c939eccf5871985a9
3
+ size 5155279
onnx/int8/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adffcc5db5d58af75af67f708559fdd9fa6740788fc296c8eb1352a98e0c2d84
3
+ size 1019761920
onnx/int8/processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
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
+ "processor_class": "Wav2Vec2Processor"
12
+ }
onnx/int8/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "152": {
36
+ "content": "|",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
46
+ "do_lower_case": false,
47
+ "eos_token": "</s>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "<pad>",
50
+ "processor_class": "Wav2Vec2Processor",
51
+ "replace_word_delimiter_char": " ",
52
+ "target_lang": null,
53
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
54
+ "unk_token": "<unk>",
55
+ "word_delimiter_token": "|"
56
+ }
onnx/int8/vocab.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 140,
3
+ "\"": 118,
4
+ "$": 127,
5
+ "%": 119,
6
+ "&": 132,
7
+ "'": 113,
8
+ ",": 109,
9
+ "-": 106,
10
+ ".": 107,
11
+ "/": 115,
12
+ "0": 66,
13
+ "1": 73,
14
+ "2": 84,
15
+ "3": 100,
16
+ "4": 96,
17
+ "5": 92,
18
+ "6": 95,
19
+ "7": 104,
20
+ "8": 98,
21
+ "9": 88,
22
+ ":": 121,
23
+ ";": 133,
24
+ "</s>": 2,
25
+ "<pad>": 0,
26
+ "<s>": 1,
27
+ "<unk>": 3,
28
+ "?": 141,
29
+ "[": 146,
30
+ "]": 147,
31
+ "a": 44,
32
+ "b": 81,
33
+ "c": 68,
34
+ "d": 71,
35
+ "e": 49,
36
+ "f": 90,
37
+ "g": 74,
38
+ "h": 67,
39
+ "i": 55,
40
+ "j": 101,
41
+ "k": 82,
42
+ "l": 60,
43
+ "m": 70,
44
+ "n": 53,
45
+ "o": 52,
46
+ "p": 75,
47
+ "q": 110,
48
+ "r": 51,
49
+ "s": 57,
50
+ "t": 61,
51
+ "u": 69,
52
+ "v": 94,
53
+ "w": 89,
54
+ "x": 108,
55
+ "y": 86,
56
+ "z": 105,
57
+ "£": 149,
58
+ "«": 124,
59
+ "°": 143,
60
+ "²": 148,
61
+ "»": 125,
62
+ "á": 128,
63
+ "ç": 126,
64
+ "é": 142,
65
+ "í": 136,
66
+ "õ": 138,
67
+ "ú": 150,
68
+ "ü": 122,
69
+ "ក": 8,
70
+ "ខ": 41,
71
+ "គ": 30,
72
+ "ឃ": 85,
73
+ "ង": 12,
74
+ "ច": 24,
75
+ "ឆ": 63,
76
+ "ជ": 29,
77
+ "ឈ": 76,
78
+ "ញ": 39,
79
+ "ដ": 18,
80
+ "ឋ": 72,
81
+ "ឌ": 83,
82
+ "ឍ": 111,
83
+ "ណ": 38,
84
+ "ត": 14,
85
+ "ថ": 42,
86
+ "ទ": 16,
87
+ "ធ": 40,
88
+ "ន": 6,
89
+ "ប": 9,
90
+ "ផ": 43,
91
+ "ព": 22,
92
+ "ភ": 45,
93
+ "ម": 11,
94
+ "យ": 17,
95
+ "រ": 7,
96
+ "ល": 13,
97
+ "វ": 26,
98
+ "ស": 10,
99
+ "ហ": 37,
100
+ "ឡ": 54,
101
+ "អ": 32,
102
+ "ឥ": 102,
103
+ "ឦ": 135,
104
+ "ឧ": 99,
105
+ "ឪ": 123,
106
+ "ឫ": 134,
107
+ "ឬ": 80,
108
+ "ឭ": 151,
109
+ "ឮ": 130,
110
+ "ឯ": 97,
111
+ "ឱ": 77,
112
+ "ឲ": 103,
113
+ "ឳ": 137,
114
+ "ា": 4,
115
+ "ិ": 19,
116
+ "ី": 25,
117
+ "ឹ": 47,
118
+ "ឺ": 56,
119
+ "ុ": 20,
120
+ "ូ": 31,
121
+ "ួ": 36,
122
+ "ើ": 27,
123
+ "ឿ": 87,
124
+ "ៀ": 64,
125
+ "េ": 21,
126
+ "ែ": 28,
127
+ "ៃ": 50,
128
+ "ោ": 33,
129
+ "ៅ": 35,
130
+ "ំ": 23,
131
+ "ះ": 34,
132
+ "ៈ": 78,
133
+ "៉": 46,
134
+ "៊": 59,
135
+ "់": 15,
136
+ "៌": 93,
137
+ "៍": 62,
138
+ "៎": 139,
139
+ "៏": 65,
140
+ "័": 58,
141
+ "្": 5,
142
+ "។": 91,
143
+ "៖": 112,
144
+ "ៗ": 79,
145
+ "០": 120,
146
+ "១": 117,
147
+ "២": 129,
148
+ "៣": 145,
149
+ "៥": 144,
150
+ "៧": 114,
151
+ "​": 48,
152
+ "—": 131,
153
+ "”": 116,
154
+ "|": 152
155
+ }