khaoulaoub
commited on
Commit
•
eb2a8ed
1
Parent(s):
ac212f8
End of training
Browse files- README.md +122 -0
- config.json +117 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-darija
|
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 |
+
# wav2vec2-darija
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4265
|
21 |
+
- Wer: 0.4101
|
22 |
+
- Cer: 0.1327
|
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: 0.0001
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
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_steps: 1000
|
48 |
+
- num_epochs: 30
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
54 |
+
| 10.5265 | 0.49 | 500 | 3.2082 | 1.0 | 0.9971 |
|
55 |
+
| 2.9629 | 0.98 | 1000 | 2.9619 | 1.0000 | 0.9357 |
|
56 |
+
| 2.6527 | 1.46 | 1500 | 1.4934 | 1.0974 | 0.4550 |
|
57 |
+
| 1.2946 | 1.95 | 2000 | 0.6904 | 0.7809 | 0.2566 |
|
58 |
+
| 0.9059 | 2.44 | 2500 | 0.5906 | 0.7002 | 0.2190 |
|
59 |
+
| 0.8133 | 2.93 | 3000 | 0.5199 | 0.6382 | 0.2049 |
|
60 |
+
| 0.7026 | 3.41 | 3500 | 0.4570 | 0.5986 | 0.1919 |
|
61 |
+
| 0.6572 | 3.9 | 4000 | 0.4238 | 0.5792 | 0.1848 |
|
62 |
+
| 0.5904 | 4.39 | 4500 | 0.4116 | 0.5637 | 0.1807 |
|
63 |
+
| 0.5593 | 4.88 | 5000 | 0.3850 | 0.5414 | 0.1734 |
|
64 |
+
| 0.5084 | 5.37 | 5500 | 0.3951 | 0.5409 | 0.1733 |
|
65 |
+
| 0.5033 | 5.85 | 6000 | 0.4449 | 0.5176 | 0.1649 |
|
66 |
+
| 0.4712 | 6.34 | 6500 | 0.5485 | 0.5172 | 0.1658 |
|
67 |
+
| 0.4459 | 6.83 | 7000 | 0.5259 | 0.5061 | 0.1623 |
|
68 |
+
| 0.4246 | 7.32 | 7500 | 0.3686 | 0.4991 | 0.1605 |
|
69 |
+
| 0.4261 | 7.8 | 8000 | 0.3663 | 0.4898 | 0.1589 |
|
70 |
+
| 0.4078 | 8.29 | 8500 | 0.3740 | 0.4858 | 0.1564 |
|
71 |
+
| 0.3783 | 8.78 | 9000 | 0.3907 | 0.4824 | 0.1566 |
|
72 |
+
| 0.3647 | 9.27 | 9500 | 0.3424 | 0.4750 | 0.1525 |
|
73 |
+
| 0.3527 | 9.76 | 10000 | 0.3444 | 0.4692 | 0.1513 |
|
74 |
+
| 0.3482 | 10.24 | 10500 | 0.3856 | 0.4692 | 0.1507 |
|
75 |
+
| 0.3338 | 10.73 | 11000 | 0.3650 | 0.4664 | 0.1512 |
|
76 |
+
| 0.3198 | 11.22 | 11500 | 0.3516 | 0.4628 | 0.1492 |
|
77 |
+
| 0.3218 | 11.71 | 12000 | 0.3660 | 0.4644 | 0.1491 |
|
78 |
+
| 0.3115 | 12.2 | 12500 | 0.3490 | 0.4545 | 0.1475 |
|
79 |
+
| 0.2977 | 12.68 | 13000 | 0.3555 | 0.4504 | 0.1451 |
|
80 |
+
| 0.2958 | 13.17 | 13500 | 0.3425 | 0.4571 | 0.1449 |
|
81 |
+
| 0.278 | 13.66 | 14000 | 0.4035 | 0.4520 | 0.1446 |
|
82 |
+
| 0.2716 | 14.15 | 14500 | 0.3552 | 0.4492 | 0.1437 |
|
83 |
+
| 0.2729 | 14.63 | 15000 | 0.3665 | 0.4470 | 0.1432 |
|
84 |
+
| 0.2691 | 15.12 | 15500 | 0.3700 | 0.4498 | 0.1444 |
|
85 |
+
| 0.2563 | 15.61 | 16000 | 0.3658 | 0.4423 | 0.1421 |
|
86 |
+
| 0.2511 | 16.1 | 16500 | 0.4152 | 0.4408 | 0.1425 |
|
87 |
+
| 0.2348 | 16.59 | 17000 | 0.4889 | 0.4375 | 0.1416 |
|
88 |
+
| 0.2437 | 17.07 | 17500 | 0.4209 | 0.4382 | 0.1413 |
|
89 |
+
| 0.2388 | 17.56 | 18000 | 0.6032 | 0.4359 | 0.1408 |
|
90 |
+
| 0.2235 | 18.05 | 18500 | 0.4831 | 0.4369 | 0.1402 |
|
91 |
+
| 0.2197 | 18.54 | 19000 | 0.4989 | 0.4345 | 0.1402 |
|
92 |
+
| 0.2285 | 19.02 | 19500 | 0.5929 | 0.4342 | 0.1393 |
|
93 |
+
| 0.2224 | 19.51 | 20000 | 0.4098 | 0.4317 | 0.1398 |
|
94 |
+
| 0.2183 | 20.0 | 20500 | 0.3547 | 0.4254 | 0.1384 |
|
95 |
+
| 0.2113 | 20.49 | 21000 | 0.3926 | 0.4324 | 0.1385 |
|
96 |
+
| 0.2125 | 20.98 | 21500 | 0.3982 | 0.4299 | 0.1386 |
|
97 |
+
| 0.201 | 21.46 | 22000 | 0.3929 | 0.4293 | 0.1389 |
|
98 |
+
| 0.2002 | 21.95 | 22500 | 0.4047 | 0.4218 | 0.1372 |
|
99 |
+
| 0.2029 | 22.44 | 23000 | 0.5153 | 0.4235 | 0.1375 |
|
100 |
+
| 0.195 | 22.93 | 23500 | 0.5601 | 0.4198 | 0.1364 |
|
101 |
+
| 0.182 | 23.41 | 24000 | 0.4596 | 0.4168 | 0.1355 |
|
102 |
+
| 0.1889 | 23.9 | 24500 | 0.4165 | 0.4209 | 0.1353 |
|
103 |
+
| 0.1795 | 24.39 | 25000 | 0.4096 | 0.4185 | 0.1352 |
|
104 |
+
| 0.1809 | 24.88 | 25500 | 0.4732 | 0.4126 | 0.1341 |
|
105 |
+
| 0.1762 | 25.37 | 26000 | 0.4324 | 0.4146 | 0.1347 |
|
106 |
+
| 0.1764 | 25.85 | 26500 | 0.4462 | 0.4160 | 0.1347 |
|
107 |
+
| 0.1805 | 26.34 | 27000 | 0.3955 | 0.4107 | 0.1333 |
|
108 |
+
| 0.1733 | 26.83 | 27500 | 0.4182 | 0.4135 | 0.1336 |
|
109 |
+
| 0.1651 | 27.32 | 28000 | 0.4111 | 0.4104 | 0.1330 |
|
110 |
+
| 0.1713 | 27.8 | 28500 | 0.4426 | 0.4126 | 0.1332 |
|
111 |
+
| 0.1766 | 28.29 | 29000 | 0.4426 | 0.4085 | 0.1328 |
|
112 |
+
| 0.1631 | 28.78 | 29500 | 0.4248 | 0.4083 | 0.1328 |
|
113 |
+
| 0.1608 | 29.27 | 30000 | 0.4334 | 0.4096 | 0.1327 |
|
114 |
+
| 0.1688 | 29.76 | 30500 | 0.4265 | 0.4101 | 0.1327 |
|
115 |
+
|
116 |
+
|
117 |
+
### Framework versions
|
118 |
+
|
119 |
+
- Transformers 4.34.0
|
120 |
+
- Pytorch 2.1.0+cu121
|
121 |
+
- Datasets 2.14.5
|
122 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
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": 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": 0.1,
|
54 |
+
"feat_quantizer_dropout": 0.0,
|
55 |
+
"final_dropout": 0.0,
|
56 |
+
"gradient_checkpointing": false,
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.1,
|
59 |
+
"hidden_size": 1024,
|
60 |
+
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 4096,
|
62 |
+
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.1,
|
64 |
+
"mask_channel_length": 10,
|
65 |
+
"mask_channel_min_space": 1,
|
66 |
+
"mask_channel_other": 0.0,
|
67 |
+
"mask_channel_prob": 0.0,
|
68 |
+
"mask_channel_selection": "static",
|
69 |
+
"mask_feature_length": 10,
|
70 |
+
"mask_feature_min_masks": 0,
|
71 |
+
"mask_feature_prob": 0.0,
|
72 |
+
"mask_time_length": 10,
|
73 |
+
"mask_time_min_masks": 2,
|
74 |
+
"mask_time_min_space": 1,
|
75 |
+
"mask_time_other": 0.0,
|
76 |
+
"mask_time_prob": 0.075,
|
77 |
+
"mask_time_selection": "static",
|
78 |
+
"model_type": "wav2vec2",
|
79 |
+
"num_adapter_layers": 3,
|
80 |
+
"num_attention_heads": 16,
|
81 |
+
"num_codevector_groups": 2,
|
82 |
+
"num_codevectors_per_group": 320,
|
83 |
+
"num_conv_pos_embedding_groups": 16,
|
84 |
+
"num_conv_pos_embeddings": 128,
|
85 |
+
"num_feat_extract_layers": 7,
|
86 |
+
"num_hidden_layers": 24,
|
87 |
+
"num_negatives": 100,
|
88 |
+
"output_hidden_size": 1024,
|
89 |
+
"pad_token_id": 34,
|
90 |
+
"proj_codevector_dim": 768,
|
91 |
+
"tdnn_dilation": [
|
92 |
+
1,
|
93 |
+
2,
|
94 |
+
3,
|
95 |
+
1,
|
96 |
+
1
|
97 |
+
],
|
98 |
+
"tdnn_dim": [
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
1500
|
104 |
+
],
|
105 |
+
"tdnn_kernel": [
|
106 |
+
5,
|
107 |
+
3,
|
108 |
+
3,
|
109 |
+
1,
|
110 |
+
1
|
111 |
+
],
|
112 |
+
"torch_dtype": "float32",
|
113 |
+
"transformers_version": "4.34.0",
|
114 |
+
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 35,
|
116 |
+
"xvector_output_dim": 512
|
117 |
+
}
|
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": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f703ed372330ad22aea323d9c162e628538dd25f906c16841df19e94aa334f1
|
3 |
+
size 1262045866
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7348ddd06571c6d07de38d27154acd64263b2c5c15c83315eb89b89c497d41fc
|
3 |
+
size 4472
|