jonatasgrosman commited on
Commit
f0819e3
1 Parent(s): d52c6d7

jonatasgrosman/exp_w2v2t_id_wavlm_s579

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ transcriptions_cv7_validation.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - id
4
+ license: apache-2.0
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - id
8
+ datasets:
9
+ - mozilla-foundation/common_voice_7_0
10
+ ---
11
+ # exp_w2v2t_id_wavlm_s579
12
+
13
+ Fine-tuned [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) for speech recognition using the train split of [Common Voice 7.0 (id)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
14
+ When using this model, make sure that your speech input is sampled at 16kHz.
15
+
16
+ This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.
17
+
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/wavlm-large",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "WavLMForCTC"
10
+ ],
11
+ "attention_dropout": 0.05,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.05,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.05,
63
+ "mask_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.05,
76
+ "mask_time_selection": "static",
77
+ "max_bucket_distance": 800,
78
+ "model_type": "wavlm",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_buckets": 320,
82
+ "num_codevector_groups": 2,
83
+ "num_codevectors_per_group": 320,
84
+ "num_conv_pos_embedding_groups": 16,
85
+ "num_conv_pos_embeddings": 128,
86
+ "num_ctc_classes": 80,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 24,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 1024,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 768,
93
+ "replace_prob": 0.5,
94
+ "tdnn_dilation": [
95
+ 1,
96
+ 2,
97
+ 3,
98
+ 1,
99
+ 1
100
+ ],
101
+ "tdnn_dim": [
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 1500
107
+ ],
108
+ "tdnn_kernel": [
109
+ 5,
110
+ 3,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
116
+ "torch_dtype": "float32",
117
+ "transformers_version": "4.15.0",
118
+ "use_weighted_layer_sum": false,
119
+ "vocab_size": 35,
120
+ "xvector_output_dim": 512
121
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84bff3a88f8efdad6be96f6c285891a2be77676555cb28ed1a1c620045a577dc
3
+ size 1262146605
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/tmp/tmp4hdr3853", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
transcriptions_cv7_test.json ADDED
The diff for this file is too large to render. See raw diff
 
transcriptions_cv7_validation.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91996ae22f5037d75da4b32e420ec4c7bf92a474ce455fb6c4515bd9c2ae974e
3
+ size 11370899
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "q": 23, "r": 24, "s": 25, "t": 26, "u": 27, "v": 28, "w": 29, "x": 30, "y": 31, "z": 32, "á": 33, "é": 34}