Hugging Face's logo

ashishabraham22
/
XLS-R_Finetuned

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
ashishabraham22 commited on
Commit
7c26574
·
verified ·
1 Parent(s): 9e20cee

End of training

Browse files
Files changed (16) hide show
  1. README.md +56 -0
  2. config.json +108 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Jul17_10-12-38_585c9177a36d/events.out.tfevents.1721211164.585c9177a36d.4186.0 +3 -0
  6. runs/Jul17_10-17-09_585c9177a36d/events.out.tfevents.1721211431.585c9177a36d.4186.1 +3 -0
  7. runs/Jul17_10-19-37_585c9177a36d/events.out.tfevents.1721211579.585c9177a36d.4186.2 +3 -0
  8. runs/Jul17_10-20-05_585c9177a36d/events.out.tfevents.1721211606.585c9177a36d.4186.3 +3 -0
  9. runs/Jul17_10-21-17_585c9177a36d/events.out.tfevents.1721211678.585c9177a36d.4186.4 +3 -0
  10. runs/Jul17_10-24-26_585c9177a36d/events.out.tfevents.1721211867.585c9177a36d.4186.5 +3 -0
  11. runs/Jul17_10-28-16_585c9177a36d/events.out.tfevents.1721212097.585c9177a36d.4186.6 +3 -0
  12. runs/Jul17_10-30-43_585c9177a36d/events.out.tfevents.1721212245.585c9177a36d.4186.7 +3 -0
  13. runs/Jul17_10-32-49_585c9177a36d/events.out.tfevents.1721212370.585c9177a36d.4186.8 +3 -0
  14. runs/Jul17_10-47-24_585c9177a36d/events.out.tfevents.1721213245.585c9177a36d.4186.9 +3 -0
  15. runs/Jul17_10-50-04_585c9177a36d/events.out.tfevents.1721213406.585c9177a36d.4186.10 +3 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: XLS-R_Finetuned
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # XLS-R_Finetuned
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.00024
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 2
40
+ - total_train_batch_size: 2
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 800
44
+ - num_epochs: 2
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.41.2
54
+ - Pytorch 2.3.0+cu121
55
+ - Datasets 2.20.0
56
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.094,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
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": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
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": 0.045,
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": 0.082,
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": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 75,
81
+ "proj_codevector_dim": 768,
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
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.41.2",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 79,
107
+ "xvector_output_dim": 512
108
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c17336c9bcbcc945c8d5948435382ae8551a165a2d43e6b86716a9d45fc137e
3
+ size 1262131380
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
+ }
runs/Jul17_10-12-38_585c9177a36d/events.out.tfevents.1721211164.585c9177a36d.4186.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bc0df24198b4b3c1ec8f284950f377f869a252e18fcb455e64a5f92d5edc4f
3
+ size 6260
runs/Jul17_10-17-09_585c9177a36d/events.out.tfevents.1721211431.585c9177a36d.4186.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc0145a259780014aa38d736d62ca880c879214c8d6d4a7e441ab32c49234e2
3
+ size 6260
runs/Jul17_10-19-37_585c9177a36d/events.out.tfevents.1721211579.585c9177a36d.4186.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc1337fe75b19e78dd0b74bc7f6b96997998a21fb6a04c7560e846a8f6ec608
3
+ size 6260
runs/Jul17_10-20-05_585c9177a36d/events.out.tfevents.1721211606.585c9177a36d.4186.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c4264ce72a65e3b0233646ce92200795bdb65b39e9fc4761915e151cf88c2e
3
+ size 6260
runs/Jul17_10-21-17_585c9177a36d/events.out.tfevents.1721211678.585c9177a36d.4186.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c9875a996af02ec117bb29fd847e8c3584b348c444c24bd612e0bef99907d9
3
+ size 6260
runs/Jul17_10-24-26_585c9177a36d/events.out.tfevents.1721211867.585c9177a36d.4186.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d3decd5873057be7c5cdc97264f8f92c69a09e596188287d84ae5f30b2066d
3
+ size 6260
runs/Jul17_10-28-16_585c9177a36d/events.out.tfevents.1721212097.585c9177a36d.4186.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9f151bd6976c24b2cfd891f59f008c3e5df05c05df7d3adcb2f9854811d725
3
+ size 6260
runs/Jul17_10-30-43_585c9177a36d/events.out.tfevents.1721212245.585c9177a36d.4186.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9a9b1e9d877c8c506c596407edaf8a0567a9b91b36f425b76ec639fe02ce39
3
+ size 6260
runs/Jul17_10-32-49_585c9177a36d/events.out.tfevents.1721212370.585c9177a36d.4186.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9dc1ce85010a130899e90359dff2d4d71d7eacbc28faaf1b4f5d61329b6f14
3
+ size 6260
runs/Jul17_10-47-24_585c9177a36d/events.out.tfevents.1721213245.585c9177a36d.4186.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94974dad6ed7cbd3f6242167ed1b57c65414415aef0140a0e8bfaa521af20283
3
+ size 12432
runs/Jul17_10-50-04_585c9177a36d/events.out.tfevents.1721213406.585c9177a36d.4186.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036c711454b4045b0483a77ba50d97abd4f1cf60dcfbde915d98eeb606fe9118
3
+ size 6607
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac998dbe3b638f368379b29eca3285f69fe2a4e7130d4b78920b4120b21e20aa
3
+ size 5112