End of training
Browse files- README.md +146 -196
- config.json +110 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- runs/Jul05_12-05-38_aitest2/events.out.tfevents.1720171214.aitest2.195429.0 +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,199 +1,149 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
-
|
33 |
-
-
|
34 |
-
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
-
|
155 |
-
### Model Architecture and Objective
|
156 |
-
|
157 |
-
[More Information Needed]
|
158 |
-
|
159 |
-
### Compute Infrastructure
|
160 |
-
|
161 |
-
[More Information Needed]
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
## Model Card Contact
|
198 |
-
|
199 |
-
[More Information Needed]
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- tr
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_17
|
10 |
+
model-index:
|
11 |
+
- name: 'Wav2Vec2-XLS-TR '
|
12 |
+
results: []
|
13 |
---
|
14 |
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# Wav2Vec2-XLS-TR
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Common Voice 17 dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5348
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 30
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
55 |
+
| 21.9538 | 0.3446 | 500 | 12.1320 |
|
56 |
+
| 7.2139 | 0.6892 | 1000 | 5.5372 |
|
57 |
+
| 4.9229 | 1.0338 | 1500 | 4.4389 |
|
58 |
+
| 4.0539 | 1.3784 | 2000 | 3.7210 |
|
59 |
+
| 3.5019 | 1.7229 | 2500 | 3.3480 |
|
60 |
+
| 3.2272 | 2.0675 | 3000 | 3.1302 |
|
61 |
+
| 2.9163 | 2.4121 | 3500 | 2.5875 |
|
62 |
+
| 1.902 | 2.7567 | 4000 | 1.5471 |
|
63 |
+
| 1.2034 | 3.1013 | 4500 | 1.1319 |
|
64 |
+
| 0.9389 | 3.4459 | 5000 | 1.0412 |
|
65 |
+
| 0.7599 | 3.7905 | 5500 | 0.8486 |
|
66 |
+
| 0.6418 | 4.1351 | 6000 | 0.7179 |
|
67 |
+
| 0.569 | 4.4797 | 6500 | 0.7109 |
|
68 |
+
| 0.5248 | 4.8243 | 7000 | 0.6470 |
|
69 |
+
| 0.4752 | 5.1688 | 7500 | 0.6298 |
|
70 |
+
| 0.4461 | 5.5134 | 8000 | 0.6198 |
|
71 |
+
| 0.4187 | 5.8580 | 8500 | 0.6224 |
|
72 |
+
| 0.3935 | 6.2026 | 9000 | 0.6116 |
|
73 |
+
| 0.3756 | 6.5472 | 9500 | 0.5536 |
|
74 |
+
| 0.3597 | 6.8918 | 10000 | 0.5263 |
|
75 |
+
| 0.3483 | 7.2364 | 10500 | 0.5179 |
|
76 |
+
| 0.3283 | 7.5810 | 11000 | 0.5054 |
|
77 |
+
| 0.3204 | 7.9256 | 11500 | 0.5200 |
|
78 |
+
| 0.3031 | 8.2702 | 12000 | 0.4984 |
|
79 |
+
| 0.2986 | 8.6147 | 12500 | 0.4846 |
|
80 |
+
| 0.2936 | 8.9593 | 13000 | 0.4984 |
|
81 |
+
| 0.2789 | 9.3039 | 13500 | 0.4888 |
|
82 |
+
| 0.2724 | 9.6485 | 14000 | 0.4654 |
|
83 |
+
| 0.2718 | 9.9931 | 14500 | 0.4553 |
|
84 |
+
| 0.2533 | 10.3377 | 15000 | 0.4506 |
|
85 |
+
| 0.2498 | 10.6823 | 15500 | 0.4983 |
|
86 |
+
| 0.2501 | 11.0269 | 16000 | 0.4835 |
|
87 |
+
| 0.2384 | 11.3715 | 16500 | 0.4749 |
|
88 |
+
| 0.2371 | 11.7161 | 17000 | 0.4877 |
|
89 |
+
| 0.2319 | 12.0606 | 17500 | 0.4806 |
|
90 |
+
| 0.2235 | 12.4052 | 18000 | 0.4874 |
|
91 |
+
| 0.2218 | 12.7498 | 18500 | 0.4565 |
|
92 |
+
| 0.2193 | 13.0944 | 19000 | 0.4733 |
|
93 |
+
| 0.2154 | 13.4390 | 19500 | 0.4747 |
|
94 |
+
| 0.2157 | 13.7836 | 20000 | 0.4694 |
|
95 |
+
| 0.2067 | 14.1282 | 20500 | 0.4848 |
|
96 |
+
| 0.2044 | 14.4728 | 21000 | 0.5092 |
|
97 |
+
| 0.2023 | 14.8174 | 21500 | 0.4752 |
|
98 |
+
| 0.1975 | 15.1620 | 22000 | 0.4852 |
|
99 |
+
| 0.1903 | 15.5065 | 22500 | 0.4891 |
|
100 |
+
| 0.1922 | 15.8511 | 23000 | 0.4825 |
|
101 |
+
| 0.1901 | 16.1957 | 23500 | 0.4836 |
|
102 |
+
| 0.1862 | 16.5403 | 24000 | 0.4838 |
|
103 |
+
| 0.1842 | 16.8849 | 24500 | 0.4897 |
|
104 |
+
| 0.1837 | 17.2295 | 25000 | 0.4920 |
|
105 |
+
| 0.1782 | 17.5741 | 25500 | 0.4937 |
|
106 |
+
| 0.1775 | 17.9187 | 26000 | 0.4868 |
|
107 |
+
| 0.1738 | 18.2633 | 26500 | 0.5107 |
|
108 |
+
| 0.1739 | 18.6079 | 27000 | 0.4943 |
|
109 |
+
| 0.1722 | 18.9524 | 27500 | 0.4740 |
|
110 |
+
| 0.1691 | 19.2970 | 28000 | 0.4965 |
|
111 |
+
| 0.1684 | 19.6416 | 28500 | 0.4834 |
|
112 |
+
| 0.1646 | 19.9862 | 29000 | 0.5187 |
|
113 |
+
| 0.1637 | 20.3308 | 29500 | 0.4979 |
|
114 |
+
| 0.1625 | 20.6754 | 30000 | 0.4945 |
|
115 |
+
| 0.1608 | 21.0200 | 30500 | 0.5149 |
|
116 |
+
| 0.1567 | 21.3646 | 31000 | 0.5030 |
|
117 |
+
| 0.1571 | 21.7092 | 31500 | 0.5013 |
|
118 |
+
| 0.1589 | 22.0538 | 32000 | 0.5269 |
|
119 |
+
| 0.1524 | 22.3983 | 32500 | 0.5191 |
|
120 |
+
| 0.1491 | 22.7429 | 33000 | 0.5200 |
|
121 |
+
| 0.1521 | 23.0875 | 33500 | 0.5206 |
|
122 |
+
| 0.149 | 23.4321 | 34000 | 0.5214 |
|
123 |
+
| 0.1505 | 23.7767 | 34500 | 0.5255 |
|
124 |
+
| 0.1516 | 24.1213 | 35000 | 0.5168 |
|
125 |
+
| 0.1479 | 24.4659 | 35500 | 0.5431 |
|
126 |
+
| 0.1476 | 24.8105 | 36000 | 0.5352 |
|
127 |
+
| 0.1433 | 25.1551 | 36500 | 0.5281 |
|
128 |
+
| 0.1464 | 25.4997 | 37000 | 0.5207 |
|
129 |
+
| 0.1444 | 25.8442 | 37500 | 0.5254 |
|
130 |
+
| 0.1466 | 26.1888 | 38000 | 0.5163 |
|
131 |
+
| 0.1424 | 26.5334 | 38500 | 0.5200 |
|
132 |
+
| 0.1375 | 26.8780 | 39000 | 0.5188 |
|
133 |
+
| 0.1428 | 27.2226 | 39500 | 0.5315 |
|
134 |
+
| 0.1376 | 27.5672 | 40000 | 0.5323 |
|
135 |
+
| 0.139 | 27.9118 | 40500 | 0.5370 |
|
136 |
+
| 0.1437 | 28.2564 | 41000 | 0.5426 |
|
137 |
+
| 0.138 | 28.6010 | 41500 | 0.5263 |
|
138 |
+
| 0.1382 | 28.9456 | 42000 | 0.5286 |
|
139 |
+
| 0.139 | 29.2901 | 42500 | 0.5302 |
|
140 |
+
| 0.139 | 29.6347 | 43000 | 0.5334 |
|
141 |
+
| 0.1356 | 29.9793 | 43500 | 0.5348 |
|
142 |
+
|
143 |
+
|
144 |
+
### Framework versions
|
145 |
+
|
146 |
+
- Transformers 4.41.2
|
147 |
+
- Pytorch 2.3.1+cu121
|
148 |
+
- Datasets 2.20.0
|
149 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 0.0,
|
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 |
+
"gradient_checkpointing": false,
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.0,
|
59 |
+
"hidden_size": 1024,
|
60 |
+
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 4096,
|
62 |
+
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.0,
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_min_masks": 0,
|
66 |
+
"mask_feature_prob": 0.0,
|
67 |
+
"mask_time_length": 10,
|
68 |
+
"mask_time_min_masks": 2,
|
69 |
+
"mask_time_prob": 0.05,
|
70 |
+
"model_type": "wav2vec2",
|
71 |
+
"num_adapter_layers": 3,
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"output_hidden_size": 1024,
|
81 |
+
"pad_token_id": 40,
|
82 |
+
"proj_codevector_dim": 768,
|
83 |
+
"tdnn_dilation": [
|
84 |
+
1,
|
85 |
+
2,
|
86 |
+
3,
|
87 |
+
1,
|
88 |
+
1
|
89 |
+
],
|
90 |
+
"tdnn_dim": [
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
512,
|
94 |
+
512,
|
95 |
+
1500
|
96 |
+
],
|
97 |
+
"tdnn_kernel": [
|
98 |
+
5,
|
99 |
+
3,
|
100 |
+
3,
|
101 |
+
1,
|
102 |
+
1
|
103 |
+
],
|
104 |
+
"torch_dtype": "float32",
|
105 |
+
"transformers_version": "4.41.2",
|
106 |
+
"use_cache": false,
|
107 |
+
"use_weighted_layer_sum": false,
|
108 |
+
"vocab_size": 43,
|
109 |
+
"xvector_output_dim": 512
|
110 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35fd478104b02b8b2db93a90f7834fc1fe754bdf6100fae9d43e98e98da31af0
|
3 |
+
size 1261983780
|
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": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
runs/Jul05_12-05-38_aitest2/events.out.tfevents.1720171214.aitest2.195429.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c602e12af1d09872b9b8f1ac2a786823826114d7d57f9541b61b86192f8a1d7
|
3 |
+
size 49044
|
tokenizer_config.json
CHANGED
@@ -39,6 +39,7 @@
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
|
|
42 |
"replace_word_delimiter_char": " ",
|
43 |
"target_lang": null,
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
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",
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f0fc17bb23db87cca9671708755607f33727c3638025448d742a75d88ec98db
|
3 |
+
size 5112
|