Hugging Face's logo

EJAD1
/
wav2vec2-mina-ft

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
EJAD1 commited on
Commit
5f40458
·
verified ·
1 Parent(s): db5990e

End of training

Browse files
Files changed (17) hide show
  1. README.md +57 -0
  2. config.json +107 -0
  3. model.safetensors +3 -0
  4. runs/Jan14_14-02-22_04f6903732ce/events.out.tfevents.1768399364.04f6903732ce.21513.0 +3 -0
  5. runs/Jan14_14-03-07_04f6903732ce/events.out.tfevents.1768399409.04f6903732ce.21513.1 +3 -0
  6. runs/Jan14_14-03-07_04f6903732ce/events.out.tfevents.1768399465.04f6903732ce.21513.2 +3 -0
  7. runs/Jan14_14-04-51_04f6903732ce/events.out.tfevents.1768399513.04f6903732ce.21513.3 +3 -0
  8. runs/Jan14_14-05-41_04f6903732ce/events.out.tfevents.1768399565.04f6903732ce.21513.4 +3 -0
  9. runs/Jan14_14-07-28_04f6903732ce/events.out.tfevents.1768399675.04f6903732ce.21513.5 +3 -0
  10. runs/Jan14_14-10-26_04f6903732ce/events.out.tfevents.1768399895.04f6903732ce.21513.6 +3 -0
  11. runs/Jan14_14-10-26_04f6903732ce/events.out.tfevents.1768399991.04f6903732ce.21513.7 +3 -0
  12. runs/Jan14_14-16-12_04f6903732ce/events.out.tfevents.1768400188.04f6903732ce.21513.8 +3 -0
  13. runs/Jan14_14-16-12_04f6903732ce/events.out.tfevents.1768400212.04f6903732ce.21513.9 +3 -0
  14. special_tokens_map.json +6 -0
  15. tokenizer_config.json +49 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/mms-1b-all
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: wav2vec2-mina-ft
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-mina-ft
16
+
17
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0003
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 8
41
+ - total_train_batch_size: 8
42
+ - optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 500
45
+ - num_epochs: 30
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.57.5
55
+ - Pytorch 2.9.0+cu126
56
+ - Datasets 4.0.0
57
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.05,
3
+ "adapter_attn_dim": 16,
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": 1024,
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": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
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": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.05,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.05,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "transformers_version": "4.57.5",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 154,
106
+ "xvector_output_dim": 512
107
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0c685a2b865fda505031ed9e8047eb9615ed2ef01251b2e03dad4abbaefe49
3
+ size 3859521176
runs/Jan14_14-02-22_04f6903732ce/events.out.tfevents.1768399364.04f6903732ce.21513.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d45090dbfd1ff2310af70295c3912773517817a261d680c05cbd64cc8b6af4
3
+ size 6398
runs/Jan14_14-03-07_04f6903732ce/events.out.tfevents.1768399409.04f6903732ce.21513.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29030cb3871238bd4ad433030e90316600597f0b8e28a29b158d649fe90385f9
3
+ size 6399
runs/Jan14_14-03-07_04f6903732ce/events.out.tfevents.1768399465.04f6903732ce.21513.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfece0c1d9df04f0cc3b24f1d7ca88380d3a4c19b774d15c265b4a05af4a1fd
3
+ size 6399
runs/Jan14_14-04-51_04f6903732ce/events.out.tfevents.1768399513.04f6903732ce.21513.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b1f9de111898f2376f9a750c97a73c868fc40dc4fb59b456dd8ab418547419
3
+ size 6400
runs/Jan14_14-05-41_04f6903732ce/events.out.tfevents.1768399565.04f6903732ce.21513.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b269780c44d09af033ce4e8e4259b5466617cd48e42b6d37648590349ba3647c
3
+ size 6399
runs/Jan14_14-07-28_04f6903732ce/events.out.tfevents.1768399675.04f6903732ce.21513.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3959c8c4e081e7104aff74fce171535583a2d160fc2b88961ead2c25f84fa5fc
3
+ size 6398
runs/Jan14_14-10-26_04f6903732ce/events.out.tfevents.1768399895.04f6903732ce.21513.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9562fbfccdd0a512c4f2da71fd4e89ef2d3075ac33e18c6a3f626e5f32bdb9
3
+ size 6398
runs/Jan14_14-10-26_04f6903732ce/events.out.tfevents.1768399991.04f6903732ce.21513.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a539778ea72aa6c165d3b6f8f9beed9fca754774452ee46676bf0835f47bd751
3
+ size 6398
runs/Jan14_14-16-12_04f6903732ce/events.out.tfevents.1768400188.04f6903732ce.21513.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1b3b93ab7891053e08720154fd0265de9fac2a01b94b57ae3d98fa2fc15527
3
+ size 6391
runs/Jan14_14-16-12_04f6903732ce/events.out.tfevents.1768400212.04f6903732ce.21513.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d14c5c7058c3b186de283da99c28de399f6083a7dc94dd85b8551718d8dea7b
3
+ size 6956
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": "eng",
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "<unk>",
48
+ "word_delimiter_token": "|"
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af930d62ed3fbe43e52722c11b4aa029288efd0775c513fec05f21a5a2d471d
3
+ size 5841
vocab.json ADDED
The diff for this file is too large to render. See raw diff