Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .ipynb_checkpoints/config-checkpoint.json +118 -0
- README.md +68 -0
- added_tokens.json +4 -0
- checkpoint-3000/added_tokens.json +4 -0
- checkpoint-3000/config.json +118 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/preprocessor_config.json +10 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +30 -0
- checkpoint-3000/tokenizer_config.json +48 -0
- checkpoint-3000/trainer_state.json +102 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-3000/vocab.json +31 -0
- checkpoint-3500/added_tokens.json +4 -0
- checkpoint-3500/config.json +118 -0
- checkpoint-3500/model.safetensors +3 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/preprocessor_config.json +10 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/special_tokens_map.json +30 -0
- checkpoint-3500/tokenizer_config.json +48 -0
- checkpoint-3500/trainer_state.json +109 -0
- checkpoint-3500/training_args.bin +3 -0
- checkpoint-3500/vocab.json +31 -0
- checkpoint-4000/added_tokens.json +4 -0
- checkpoint-4000/config.json +118 -0
- checkpoint-4000/model.safetensors +3 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/preprocessor_config.json +10 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/special_tokens_map.json +30 -0
- checkpoint-4000/tokenizer_config.json +48 -0
- checkpoint-4000/trainer_state.json +125 -0
- checkpoint-4000/training_args.bin +3 -0
- checkpoint-4000/vocab.json +31 -0
- checkpoint-4500/added_tokens.json +4 -0
- checkpoint-4500/config.json +118 -0
- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/preprocessor_config.json +10 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/special_tokens_map.json +30 -0
- checkpoint-4500/tokenizer_config.json +48 -0
- checkpoint-4500/trainer_state.json +132 -0
- checkpoint-4500/training_args.bin +3 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
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 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 28,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: results
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# results
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.0314
|
21 |
+
- Wer: 1.0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 30
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:-------:|:----:|:---------------:|:---:|
|
56 |
+
| 2.8609 | 5.7143 | 1000 | 3.1199 | 1.0 |
|
57 |
+
| 2.8589 | 11.4286 | 2000 | 3.0515 | 1.0 |
|
58 |
+
| 2.8587 | 17.1429 | 3000 | 2.9922 | 1.0 |
|
59 |
+
| 2.856 | 22.8571 | 4000 | 3.0177 | 1.0 |
|
60 |
+
| 2.8531 | 28.5714 | 5000 | 3.0314 | 1.0 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.41.1
|
66 |
+
- Pytorch 2.3.0+cu121
|
67 |
+
- Datasets 2.19.1
|
68 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
checkpoint-3000/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
checkpoint-3000/config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
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 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 28,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3057d96dc780ed10a08e0805f8894f3be2fd687c40e169bcad108bc23c858b17
|
3 |
+
size 377611120
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfb37c540edf376ce6a31ec0d63fd8890e0d7e577cac31a576fec618f977b03e
|
3 |
+
size 755348794
|
checkpoint-3000/preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f0a16b818a012c97aab56f895a95a490bff11514b9c74acf7d1222b2c806984
|
3 |
+
size 14308
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:657dc5b82fa7223b420413a7de9e568ab43580637ab10908da5c9162475c8968
|
3 |
+
size 1064
|
checkpoint-3000/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-3000/tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"27": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"28": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"29": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"30": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.142857142857142,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 3000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.857142857142857,
|
13 |
+
"grad_norm": 0.991371750831604,
|
14 |
+
"learning_rate": 9.8e-05,
|
15 |
+
"loss": 3.541,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 5.714285714285714,
|
20 |
+
"grad_norm": 0.3066103756427765,
|
21 |
+
"learning_rate": 8.96842105263158e-05,
|
22 |
+
"loss": 2.8609,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 5.714285714285714,
|
27 |
+
"eval_loss": 3.1199309825897217,
|
28 |
+
"eval_runtime": 29.6116,
|
29 |
+
"eval_samples_per_second": 23.639,
|
30 |
+
"eval_steps_per_second": 2.972,
|
31 |
+
"eval_wer": 1.0,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 8.571428571428571,
|
36 |
+
"grad_norm": 0.7332219481468201,
|
37 |
+
"learning_rate": 7.915789473684211e-05,
|
38 |
+
"loss": 2.8625,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 11.428571428571429,
|
43 |
+
"grad_norm": 0.29804107546806335,
|
44 |
+
"learning_rate": 6.863157894736843e-05,
|
45 |
+
"loss": 2.8589,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 11.428571428571429,
|
50 |
+
"eval_loss": 3.051466941833496,
|
51 |
+
"eval_runtime": 29.5006,
|
52 |
+
"eval_samples_per_second": 23.728,
|
53 |
+
"eval_steps_per_second": 2.983,
|
54 |
+
"eval_wer": 1.0,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 14.285714285714286,
|
59 |
+
"grad_norm": 1.4042483568191528,
|
60 |
+
"learning_rate": 5.810526315789474e-05,
|
61 |
+
"loss": 2.8584,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 17.142857142857142,
|
66 |
+
"grad_norm": 0.9517878890037537,
|
67 |
+
"learning_rate": 4.7578947368421054e-05,
|
68 |
+
"loss": 2.8587,
|
69 |
+
"step": 3000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 17.142857142857142,
|
73 |
+
"eval_loss": 2.99222993850708,
|
74 |
+
"eval_runtime": 29.1002,
|
75 |
+
"eval_samples_per_second": 24.055,
|
76 |
+
"eval_steps_per_second": 3.024,
|
77 |
+
"eval_wer": 1.0,
|
78 |
+
"step": 3000
|
79 |
+
}
|
80 |
+
],
|
81 |
+
"logging_steps": 500,
|
82 |
+
"max_steps": 5250,
|
83 |
+
"num_input_tokens_seen": 0,
|
84 |
+
"num_train_epochs": 30,
|
85 |
+
"save_steps": 500,
|
86 |
+
"stateful_callbacks": {
|
87 |
+
"TrainerControl": {
|
88 |
+
"args": {
|
89 |
+
"should_epoch_stop": false,
|
90 |
+
"should_evaluate": false,
|
91 |
+
"should_log": false,
|
92 |
+
"should_save": true,
|
93 |
+
"should_training_stop": false
|
94 |
+
},
|
95 |
+
"attributes": {}
|
96 |
+
}
|
97 |
+
},
|
98 |
+
"total_flos": 3.895420904615186e+18,
|
99 |
+
"train_batch_size": 8,
|
100 |
+
"trial_name": null,
|
101 |
+
"trial_params": null
|
102 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
|
3 |
+
size 5048
|
checkpoint-3000/vocab.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 28,
|
3 |
+
"[UNK]": 27,
|
4 |
+
"a": 0,
|
5 |
+
"b": 2,
|
6 |
+
"c": 9,
|
7 |
+
"d": 8,
|
8 |
+
"e": 1,
|
9 |
+
"f": 4,
|
10 |
+
"g": 14,
|
11 |
+
"h": 16,
|
12 |
+
"i": 19,
|
13 |
+
"j": 11,
|
14 |
+
"k": 5,
|
15 |
+
"l": 7,
|
16 |
+
"m": 17,
|
17 |
+
"n": 25,
|
18 |
+
"o": 18,
|
19 |
+
"p": 22,
|
20 |
+
"q": 26,
|
21 |
+
"r": 23,
|
22 |
+
"s": 3,
|
23 |
+
"t": 15,
|
24 |
+
"u": 13,
|
25 |
+
"v": 6,
|
26 |
+
"w": 21,
|
27 |
+
"x": 12,
|
28 |
+
"y": 10,
|
29 |
+
"z": 20,
|
30 |
+
"|": 24
|
31 |
+
}
|
checkpoint-3500/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
checkpoint-3500/config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
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 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 28,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
checkpoint-3500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b636a2a00705de0138c45a075ee49f6489d549b9fe202566c887306f3c0a985
|
3 |
+
size 377611120
|
checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a39513d3b8b4714cc99620cc17b4bd80bd7b4530512b800054e8fd2292f0237
|
3 |
+
size 755348794
|
checkpoint-3500/preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
checkpoint-3500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c9e575475bfcd3e70bda3ee27b6b421707d9231fb7f15399d4eb90c258afb3d
|
3 |
+
size 14308
|
checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02995736038cfa25f80743d92c8376d0ee0a7847ccaffabc22cd5c173b080898
|
3 |
+
size 1064
|
checkpoint-3500/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-3500/tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"27": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"28": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"29": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"30": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
checkpoint-3500/trainer_state.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 3500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.857142857142857,
|
13 |
+
"grad_norm": 0.991371750831604,
|
14 |
+
"learning_rate": 9.8e-05,
|
15 |
+
"loss": 3.541,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 5.714285714285714,
|
20 |
+
"grad_norm": 0.3066103756427765,
|
21 |
+
"learning_rate": 8.96842105263158e-05,
|
22 |
+
"loss": 2.8609,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 5.714285714285714,
|
27 |
+
"eval_loss": 3.1199309825897217,
|
28 |
+
"eval_runtime": 29.6116,
|
29 |
+
"eval_samples_per_second": 23.639,
|
30 |
+
"eval_steps_per_second": 2.972,
|
31 |
+
"eval_wer": 1.0,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 8.571428571428571,
|
36 |
+
"grad_norm": 0.7332219481468201,
|
37 |
+
"learning_rate": 7.915789473684211e-05,
|
38 |
+
"loss": 2.8625,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 11.428571428571429,
|
43 |
+
"grad_norm": 0.29804107546806335,
|
44 |
+
"learning_rate": 6.863157894736843e-05,
|
45 |
+
"loss": 2.8589,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 11.428571428571429,
|
50 |
+
"eval_loss": 3.051466941833496,
|
51 |
+
"eval_runtime": 29.5006,
|
52 |
+
"eval_samples_per_second": 23.728,
|
53 |
+
"eval_steps_per_second": 2.983,
|
54 |
+
"eval_wer": 1.0,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 14.285714285714286,
|
59 |
+
"grad_norm": 1.4042483568191528,
|
60 |
+
"learning_rate": 5.810526315789474e-05,
|
61 |
+
"loss": 2.8584,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 17.142857142857142,
|
66 |
+
"grad_norm": 0.9517878890037537,
|
67 |
+
"learning_rate": 4.7578947368421054e-05,
|
68 |
+
"loss": 2.8587,
|
69 |
+
"step": 3000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 17.142857142857142,
|
73 |
+
"eval_loss": 2.99222993850708,
|
74 |
+
"eval_runtime": 29.1002,
|
75 |
+
"eval_samples_per_second": 24.055,
|
76 |
+
"eval_steps_per_second": 3.024,
|
77 |
+
"eval_wer": 1.0,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 20.0,
|
82 |
+
"grad_norm": 1.560330867767334,
|
83 |
+
"learning_rate": 3.7052631578947375e-05,
|
84 |
+
"loss": 2.8581,
|
85 |
+
"step": 3500
|
86 |
+
}
|
87 |
+
],
|
88 |
+
"logging_steps": 500,
|
89 |
+
"max_steps": 5250,
|
90 |
+
"num_input_tokens_seen": 0,
|
91 |
+
"num_train_epochs": 30,
|
92 |
+
"save_steps": 500,
|
93 |
+
"stateful_callbacks": {
|
94 |
+
"TrainerControl": {
|
95 |
+
"args": {
|
96 |
+
"should_epoch_stop": false,
|
97 |
+
"should_evaluate": false,
|
98 |
+
"should_log": false,
|
99 |
+
"should_save": true,
|
100 |
+
"should_training_stop": false
|
101 |
+
},
|
102 |
+
"attributes": {}
|
103 |
+
}
|
104 |
+
},
|
105 |
+
"total_flos": 4.5374223294573235e+18,
|
106 |
+
"train_batch_size": 8,
|
107 |
+
"trial_name": null,
|
108 |
+
"trial_params": null
|
109 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
|
3 |
+
size 5048
|
checkpoint-3500/vocab.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 28,
|
3 |
+
"[UNK]": 27,
|
4 |
+
"a": 0,
|
5 |
+
"b": 2,
|
6 |
+
"c": 9,
|
7 |
+
"d": 8,
|
8 |
+
"e": 1,
|
9 |
+
"f": 4,
|
10 |
+
"g": 14,
|
11 |
+
"h": 16,
|
12 |
+
"i": 19,
|
13 |
+
"j": 11,
|
14 |
+
"k": 5,
|
15 |
+
"l": 7,
|
16 |
+
"m": 17,
|
17 |
+
"n": 25,
|
18 |
+
"o": 18,
|
19 |
+
"p": 22,
|
20 |
+
"q": 26,
|
21 |
+
"r": 23,
|
22 |
+
"s": 3,
|
23 |
+
"t": 15,
|
24 |
+
"u": 13,
|
25 |
+
"v": 6,
|
26 |
+
"w": 21,
|
27 |
+
"x": 12,
|
28 |
+
"y": 10,
|
29 |
+
"z": 20,
|
30 |
+
"|": 24
|
31 |
+
}
|
checkpoint-4000/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
checkpoint-4000/config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
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 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 28,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
checkpoint-4000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e31a0571b00e2e106f57c2d89f9bfa2071529f941ba07b1c0d43d30fc1e6f9b
|
3 |
+
size 377611120
|
checkpoint-4000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04ff86da5e675a3e049910b59212e1b781f6c7a29ecf8af7630658dae6dabaf0
|
3 |
+
size 755348794
|
checkpoint-4000/preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
checkpoint-4000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3166ef885c5cd11436318692cfb6445383e1aee770da912b41a66a114f8fcee3
|
3 |
+
size 14308
|
checkpoint-4000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68f0db999c1f2b233c421b54d04dab160ff4dbe060c33128f45c6518834cabe6
|
3 |
+
size 1064
|
checkpoint-4000/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-4000/tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"27": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"28": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"29": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"30": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
checkpoint-4000/trainer_state.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 22.857142857142858,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 4000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.857142857142857,
|
13 |
+
"grad_norm": 0.991371750831604,
|
14 |
+
"learning_rate": 9.8e-05,
|
15 |
+
"loss": 3.541,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 5.714285714285714,
|
20 |
+
"grad_norm": 0.3066103756427765,
|
21 |
+
"learning_rate": 8.96842105263158e-05,
|
22 |
+
"loss": 2.8609,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 5.714285714285714,
|
27 |
+
"eval_loss": 3.1199309825897217,
|
28 |
+
"eval_runtime": 29.6116,
|
29 |
+
"eval_samples_per_second": 23.639,
|
30 |
+
"eval_steps_per_second": 2.972,
|
31 |
+
"eval_wer": 1.0,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 8.571428571428571,
|
36 |
+
"grad_norm": 0.7332219481468201,
|
37 |
+
"learning_rate": 7.915789473684211e-05,
|
38 |
+
"loss": 2.8625,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 11.428571428571429,
|
43 |
+
"grad_norm": 0.29804107546806335,
|
44 |
+
"learning_rate": 6.863157894736843e-05,
|
45 |
+
"loss": 2.8589,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 11.428571428571429,
|
50 |
+
"eval_loss": 3.051466941833496,
|
51 |
+
"eval_runtime": 29.5006,
|
52 |
+
"eval_samples_per_second": 23.728,
|
53 |
+
"eval_steps_per_second": 2.983,
|
54 |
+
"eval_wer": 1.0,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 14.285714285714286,
|
59 |
+
"grad_norm": 1.4042483568191528,
|
60 |
+
"learning_rate": 5.810526315789474e-05,
|
61 |
+
"loss": 2.8584,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 17.142857142857142,
|
66 |
+
"grad_norm": 0.9517878890037537,
|
67 |
+
"learning_rate": 4.7578947368421054e-05,
|
68 |
+
"loss": 2.8587,
|
69 |
+
"step": 3000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 17.142857142857142,
|
73 |
+
"eval_loss": 2.99222993850708,
|
74 |
+
"eval_runtime": 29.1002,
|
75 |
+
"eval_samples_per_second": 24.055,
|
76 |
+
"eval_steps_per_second": 3.024,
|
77 |
+
"eval_wer": 1.0,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 20.0,
|
82 |
+
"grad_norm": 1.560330867767334,
|
83 |
+
"learning_rate": 3.7052631578947375e-05,
|
84 |
+
"loss": 2.8581,
|
85 |
+
"step": 3500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 22.857142857142858,
|
89 |
+
"grad_norm": 0.43670666217803955,
|
90 |
+
"learning_rate": 2.652631578947369e-05,
|
91 |
+
"loss": 2.856,
|
92 |
+
"step": 4000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 22.857142857142858,
|
96 |
+
"eval_loss": 3.0176596641540527,
|
97 |
+
"eval_runtime": 30.2333,
|
98 |
+
"eval_samples_per_second": 23.153,
|
99 |
+
"eval_steps_per_second": 2.911,
|
100 |
+
"eval_wer": 1.0,
|
101 |
+
"step": 4000
|
102 |
+
}
|
103 |
+
],
|
104 |
+
"logging_steps": 500,
|
105 |
+
"max_steps": 5250,
|
106 |
+
"num_input_tokens_seen": 0,
|
107 |
+
"num_train_epochs": 30,
|
108 |
+
"save_steps": 500,
|
109 |
+
"stateful_callbacks": {
|
110 |
+
"TrainerControl": {
|
111 |
+
"args": {
|
112 |
+
"should_epoch_stop": false,
|
113 |
+
"should_evaluate": false,
|
114 |
+
"should_log": false,
|
115 |
+
"should_save": true,
|
116 |
+
"should_training_stop": false
|
117 |
+
},
|
118 |
+
"attributes": {}
|
119 |
+
}
|
120 |
+
},
|
121 |
+
"total_flos": 5.192300868316301e+18,
|
122 |
+
"train_batch_size": 8,
|
123 |
+
"trial_name": null,
|
124 |
+
"trial_params": null
|
125 |
+
}
|
checkpoint-4000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
|
3 |
+
size 5048
|
checkpoint-4000/vocab.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 28,
|
3 |
+
"[UNK]": 27,
|
4 |
+
"a": 0,
|
5 |
+
"b": 2,
|
6 |
+
"c": 9,
|
7 |
+
"d": 8,
|
8 |
+
"e": 1,
|
9 |
+
"f": 4,
|
10 |
+
"g": 14,
|
11 |
+
"h": 16,
|
12 |
+
"i": 19,
|
13 |
+
"j": 11,
|
14 |
+
"k": 5,
|
15 |
+
"l": 7,
|
16 |
+
"m": 17,
|
17 |
+
"n": 25,
|
18 |
+
"o": 18,
|
19 |
+
"p": 22,
|
20 |
+
"q": 26,
|
21 |
+
"r": 23,
|
22 |
+
"s": 3,
|
23 |
+
"t": 15,
|
24 |
+
"u": 13,
|
25 |
+
"v": 6,
|
26 |
+
"w": 21,
|
27 |
+
"x": 12,
|
28 |
+
"y": 10,
|
29 |
+
"z": 20,
|
30 |
+
"|": 24
|
31 |
+
}
|
checkpoint-4500/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
checkpoint-4500/config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
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 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 28,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.41.1",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
checkpoint-4500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ac7574a6db8eade496f8281543ec513e1f42adfb87048e58fc90f5d0fcc4efc
|
3 |
+
size 377611120
|
checkpoint-4500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2be17cffff3ec12710b8d447c759fd8bca1508415e593aed3597c954b62a0ce
|
3 |
+
size 755348794
|
checkpoint-4500/preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
checkpoint-4500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f9f4346ae9d81f950d14851002e0f180df4cdbd30f07b619c9dba2119c8f4fb
|
3 |
+
size 14244
|
checkpoint-4500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0149f57fc12864b688e1f2f8232baf86c1d67599df5810e19f880a1e9e37f825
|
3 |
+
size 1064
|
checkpoint-4500/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-4500/tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"27": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"28": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"29": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"30": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
checkpoint-4500/trainer_state.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 25.714285714285715,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 4500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.857142857142857,
|
13 |
+
"grad_norm": 0.991371750831604,
|
14 |
+
"learning_rate": 9.8e-05,
|
15 |
+
"loss": 3.541,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 5.714285714285714,
|
20 |
+
"grad_norm": 0.3066103756427765,
|
21 |
+
"learning_rate": 8.96842105263158e-05,
|
22 |
+
"loss": 2.8609,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 5.714285714285714,
|
27 |
+
"eval_loss": 3.1199309825897217,
|
28 |
+
"eval_runtime": 29.6116,
|
29 |
+
"eval_samples_per_second": 23.639,
|
30 |
+
"eval_steps_per_second": 2.972,
|
31 |
+
"eval_wer": 1.0,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 8.571428571428571,
|
36 |
+
"grad_norm": 0.7332219481468201,
|
37 |
+
"learning_rate": 7.915789473684211e-05,
|
38 |
+
"loss": 2.8625,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 11.428571428571429,
|
43 |
+
"grad_norm": 0.29804107546806335,
|
44 |
+
"learning_rate": 6.863157894736843e-05,
|
45 |
+
"loss": 2.8589,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 11.428571428571429,
|
50 |
+
"eval_loss": 3.051466941833496,
|
51 |
+
"eval_runtime": 29.5006,
|
52 |
+
"eval_samples_per_second": 23.728,
|
53 |
+
"eval_steps_per_second": 2.983,
|
54 |
+
"eval_wer": 1.0,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 14.285714285714286,
|
59 |
+
"grad_norm": 1.4042483568191528,
|
60 |
+
"learning_rate": 5.810526315789474e-05,
|
61 |
+
"loss": 2.8584,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 17.142857142857142,
|
66 |
+
"grad_norm": 0.9517878890037537,
|
67 |
+
"learning_rate": 4.7578947368421054e-05,
|
68 |
+
"loss": 2.8587,
|
69 |
+
"step": 3000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 17.142857142857142,
|
73 |
+
"eval_loss": 2.99222993850708,
|
74 |
+
"eval_runtime": 29.1002,
|
75 |
+
"eval_samples_per_second": 24.055,
|
76 |
+
"eval_steps_per_second": 3.024,
|
77 |
+
"eval_wer": 1.0,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 20.0,
|
82 |
+
"grad_norm": 1.560330867767334,
|
83 |
+
"learning_rate": 3.7052631578947375e-05,
|
84 |
+
"loss": 2.8581,
|
85 |
+
"step": 3500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 22.857142857142858,
|
89 |
+
"grad_norm": 0.43670666217803955,
|
90 |
+
"learning_rate": 2.652631578947369e-05,
|
91 |
+
"loss": 2.856,
|
92 |
+
"step": 4000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 22.857142857142858,
|
96 |
+
"eval_loss": 3.0176596641540527,
|
97 |
+
"eval_runtime": 30.2333,
|
98 |
+
"eval_samples_per_second": 23.153,
|
99 |
+
"eval_steps_per_second": 2.911,
|
100 |
+
"eval_wer": 1.0,
|
101 |
+
"step": 4000
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 25.714285714285715,
|
105 |
+
"grad_norm": 1.1510722637176514,
|
106 |
+
"learning_rate": 1.6000000000000003e-05,
|
107 |
+
"loss": 2.8548,
|
108 |
+
"step": 4500
|
109 |
+
}
|
110 |
+
],
|
111 |
+
"logging_steps": 500,
|
112 |
+
"max_steps": 5250,
|
113 |
+
"num_input_tokens_seen": 0,
|
114 |
+
"num_train_epochs": 30,
|
115 |
+
"save_steps": 500,
|
116 |
+
"stateful_callbacks": {
|
117 |
+
"TrainerControl": {
|
118 |
+
"args": {
|
119 |
+
"should_epoch_stop": false,
|
120 |
+
"should_evaluate": false,
|
121 |
+
"should_log": false,
|
122 |
+
"should_save": true,
|
123 |
+
"should_training_stop": false
|
124 |
+
},
|
125 |
+
"attributes": {}
|
126 |
+
}
|
127 |
+
},
|
128 |
+
"total_flos": 5.835659411682157e+18,
|
129 |
+
"train_batch_size": 8,
|
130 |
+
"trial_name": null,
|
131 |
+
"trial_params": null
|
132 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
|
3 |
+
size 5048
|