jonatasgrosman commited on
Commit
a198274
1 Parent(s): b1bbb74

jonatasgrosman/exp_w2v2t_it_hubert_s474

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_hubert_s474
12
+
13
+ Fine-tuned [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) 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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/hubert-large-ll60k",
3
+ "activation_dropout": 0.05,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertForCTC"
7
+ ],
8
+ "attention_dropout": 0.05,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": true,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": true,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_dropout": 0.0,
45
+ "feat_extract_norm": "layer",
46
+ "feat_proj_dropout": 0.05,
47
+ "feat_proj_layer_norm": true,
48
+ "final_dropout": 0.05,
49
+ "gradient_checkpointing": false,
50
+ "hidden_act": "gelu",
51
+ "hidden_dropout": 0.05,
52
+ "hidden_size": 1024,
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 4096,
55
+ "layer_norm_eps": 1e-05,
56
+ "layerdrop": 0.05,
57
+ "mask_channel_length": 10,
58
+ "mask_channel_min_space": 1,
59
+ "mask_channel_other": 0.0,
60
+ "mask_channel_prob": 0.0,
61
+ "mask_channel_selection": "static",
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_min_space": 1,
68
+ "mask_time_other": 0.0,
69
+ "mask_time_prob": 0.05,
70
+ "mask_time_selection": "static",
71
+ "model_type": "hubert",
72
+ "num_attention_heads": 16,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "pad_token_id": 0,
78
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
79
+ "torch_dtype": "float32",
80
+ "transformers_version": "4.15.0",
81
+ "use_weighted_layer_sum": false,
82
+ "vocab_size": 46
83
+ }
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 sha256:5d515aa5bf7a1076bc726c3686ee27edfc492a53e7cbcb412d4db68efc1a70d7
3
+ size 1262110705
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/tmp688sptq9", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
transcriptions_cv7_test.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc379cfbff9a8487ebc1380cadb224144f92d893cf5ffebbc0d9eead7d9d1825
3
+ size 78727575
transcriptions_cv7_validation.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60b98414993c5609019156bc0a9847d99fcd077c6cb949e9f861147223e9b49
3
+ size 78125935
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}