jonatasgrosman commited on
Commit
60afae3
1 Parent(s): 9fdb98d

jonatasgrosman/exp_w2v2t_it_unispeech-sat_s500

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_unispeech-sat_s500
12
+
13
+ Fine-tuned [microsoft/unispeech-sat-large](https://huggingface.co/microsoft/unispeech-sat-large) 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 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/unispeech-sat-large",
3
+ "activation_dropout": 0.05,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "UniSpeechSatForCTC"
7
+ ],
8
+ "attention_dropout": 0.05,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": false,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "sum",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.05,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.05,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.05,
54
+ "hidden_size": 1024,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 4096,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.05,
59
+ "mask_feature_length": 10,
60
+ "mask_feature_min_masks": 0,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_masks": 2,
64
+ "mask_time_prob": 0.05,
65
+ "model_type": "unispeech-sat",
66
+ "num_attention_heads": 16,
67
+ "num_clusters": 504,
68
+ "num_codevector_groups": 2,
69
+ "num_codevectors_per_group": 320,
70
+ "num_conv_pos_embedding_groups": 16,
71
+ "num_conv_pos_embeddings": 128,
72
+ "num_feat_extract_layers": 7,
73
+ "num_hidden_layers": 24,
74
+ "num_negatives": 100,
75
+ "pad_token_id": 0,
76
+ "proj_codevector_dim": 768,
77
+ "tdnn_dilation": [
78
+ 1,
79
+ 2,
80
+ 3,
81
+ 1,
82
+ 1
83
+ ],
84
+ "tdnn_dim": [
85
+ 512,
86
+ 512,
87
+ 512,
88
+ 512,
89
+ 1500
90
+ ],
91
+ "tdnn_kernel": [
92
+ 5,
93
+ 3,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.15.0",
101
+ "use_weighted_layer_sum": false,
102
+ "vocab_size": 46,
103
+ "xvector_output_dim": 512
104
+ }
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 sha256:60fef2f73bb028d8d7a2f8f1f2ff64ea5e499aa0c824e9db9f02668ae8719e14
3
+ size 1262099519
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/tmpzxd4iwtm", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
transcriptions_cv7_test.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62e4bca116c3e6e88a0324a2ead1f70e878c78d34ffc5030e150931d74c7548
3
+ size 80478737
transcriptions_cv7_validation.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4cc589a407b5cc0cf9efb029760a885805b487dd496991a4e70e13a531364d
3
+ size 79895520
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}