jonatasgrosman commited on
Commit
e2a61ec
1 Parent(s): cf06af0

jonatasgrosman/exp_w2v2t_it_vp-sv_s791

Browse files
.gitattributes CHANGED
@@ -25,3 +25,5 @@ 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_test.json filter=lfs diff=lfs merge=lfs -text
29
+ transcriptions_cv7_validation.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - it
4
+ license: apache-2.0
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - it
8
+ datasets:
9
+ - mozilla-foundation/common_voice_7_0
10
+ ---
11
+ # exp_w2v2t_it_vp-sv_s791
12
+
13
+ Fine-tuned [facebook/wav2vec2-large-sv-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-sv-voxpopuli) for speech recognition using the train split of [Common Voice 7.0 (it)](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 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-sv-voxpopuli",
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
+ "Wav2Vec2ForCTC"
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": 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": "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
+ "model_type": "wav2vec2",
78
+ "num_adapter_layers": 3,
79
+ "num_attention_heads": 16,
80
+ "num_codevector_groups": 2,
81
+ "num_codevectors_per_group": 320,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 24,
86
+ "num_negatives": 100,
87
+ "output_hidden_size": 1024,
88
+ "pad_token_id": 0,
89
+ "proj_codevector_dim": 768,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.15.0",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 46,
115
+ "xvector_output_dim": 512
116
+ }
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,
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 sha256:61fb11236f0c5e5d34b0c92c95e8025778d19238eb4b67ae424ebe14a8b65f1f
3
+ size 1262112241
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/tmpy3iyu85r", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
transcriptions_cv7_test.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570f4d4e8377ae32da971ff10503a119f1527aca4cee442a27c44b06474a4d9c
3
+ size 79661405
transcriptions_cv7_validation.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40722fc3562972c19083a03984b459da8eef10b65ca3804911b8326d9bb4229d
3
+ size 79075861
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, "à": 33, "á": 34, "è": 35, "é": 36, "ì": 37, "í": 38, "ò": 39, "ó": 40, "ù": 41, "ú": 42, "č": 43, "ō": 44, "š": 45}