Hugging Face's logo

FormosanBankDemos
/
xlsr_Amis

Automatic Speech Recognition
Transformers
Safetensors
Amis
wav2vec2
speech-recognition
xlsr
ctc
Model card Files
xet
Community
hunterschep commited on
Commit
b3ee513
·
verified ·
1 Parent(s): ac8cb11

Upload 6 files

Browse files
Files changed (6) hide show
  1. README.md +23 -3
  2. config.json +117 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. tokenizer_config.json +13 -0
  6. vocab.json +56 -0
README.md CHANGED
@@ -1,3 +1,23 @@
1
- ---
2
- license: cc-by-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ami
3
+ license: cc-by-4.0
4
+ library_name: transformers
5
+ tags:
6
+ - speech-recognition
7
+ - wav2vec2
8
+ - xlsr
9
+ - ctc
10
+ ---
11
+
12
+ # XLSR-Amis ASR Model
13
+
14
+ Fine-tuned XLSR (wav2vec2) model for Automatic Speech Recognition in **Amis**.
15
+
16
+ ## Usage
17
+
18
+ ```python
19
+ from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
20
+
21
+ processor = Wav2Vec2Processor.from_pretrained("FormosanBankDemos/xlsr_Amis")
22
+ model = Wav2Vec2ForCTC.from_pretrained("FormosanBankDemos/xlsr_Amis")
23
+
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
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": "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": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.0,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.0,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
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_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 56,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.31.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 57,
116
+ "xvector_output_dim": 512
117
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87daefd36c0332f7b056a2db774bb6d95a49a9bdc54598f2479acc371109ba1
3
+ size 1262041148
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "'": 2,
4
+ "(": 3,
5
+ ")": 4,
6
+ "/": 5,
7
+ "0": 6,
8
+ "1": 7,
9
+ "2": 8,
10
+ "3": 9,
11
+ "4": 10,
12
+ "5": 11,
13
+ "6": 12,
14
+ "7": 13,
15
+ "8": 14,
16
+ "9": 15,
17
+ "=": 16,
18
+ "^": 17,
19
+ "a": 18,
20
+ "c": 19,
21
+ "d": 20,
22
+ "e": 21,
23
+ "f": 22,
24
+ "g": 23,
25
+ "h": 24,
26
+ "i": 25,
27
+ "k": 26,
28
+ "l": 27,
29
+ "m": 28,
30
+ "n": 29,
31
+ "o": 30,
32
+ "p": 31,
33
+ "q": 32,
34
+ "r": 33,
35
+ "s": 34,
36
+ "t": 35,
37
+ "u": 36,
38
+ "v": 37,
39
+ "w": 38,
40
+ "x": 39,
41
+ "y": 40,
42
+ "z": 41,
43
+ "|": 0,
44
+ "~": 42,
45
+ "ǃ": 43,
46
+ "—": 44,
47
+ "―": 45,
48
+ "’": 46,
49
+ "“": 47,
50
+ "”": 48,
51
+ "…": 49,
52
+ "藝": 50,
53
+ "術": 51,
54
+ "！": 52,
55
+ "？": 53
56
+ }