scarlett623
commited on
Commit
•
f2d3189
1
Parent(s):
5c44501
End of training
Browse files- README.md +104 -0
- config.json +109 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-timit-xls-r-300m-colab
|
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-timit-xls-r-300m-colab
|
17 |
+
|
18 |
+
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.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3293
|
21 |
+
- Wer: 0.2879
|
22 |
+
- Cer: 0.0927
|
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 |
+
| No log | 0.69 | 400 | 3.1501 | 1.0 | 0.9865 |
|
55 |
+
| 4.3829 | 1.38 | 800 | 2.9694 | 1.0 | 0.9865 |
|
56 |
+
| 2.6389 | 2.08 | 1200 | 0.6558 | 0.5876 | 0.1878 |
|
57 |
+
| 0.9293 | 2.77 | 1600 | 0.4232 | 0.4722 | 0.1462 |
|
58 |
+
| 0.5686 | 3.46 | 2000 | 0.3513 | 0.4118 | 0.1279 |
|
59 |
+
| 0.5686 | 4.15 | 2400 | 0.3246 | 0.3994 | 0.1227 |
|
60 |
+
| 0.4388 | 4.84 | 2800 | 0.3037 | 0.3716 | 0.1158 |
|
61 |
+
| 0.3431 | 5.54 | 3200 | 0.3055 | 0.3674 | 0.1158 |
|
62 |
+
| 0.3164 | 6.23 | 3600 | 0.2973 | 0.3589 | 0.1128 |
|
63 |
+
| 0.2678 | 6.92 | 4000 | 0.3053 | 0.3421 | 0.1080 |
|
64 |
+
| 0.2678 | 7.61 | 4400 | 0.3058 | 0.3435 | 0.1083 |
|
65 |
+
| 0.2376 | 8.3 | 4800 | 0.3144 | 0.3408 | 0.1094 |
|
66 |
+
| 0.2199 | 9.0 | 5200 | 0.3177 | 0.3371 | 0.1052 |
|
67 |
+
| 0.1988 | 9.69 | 5600 | 0.3123 | 0.3299 | 0.1057 |
|
68 |
+
| 0.1816 | 10.38 | 6000 | 0.2918 | 0.3282 | 0.1049 |
|
69 |
+
| 0.1816 | 11.07 | 6400 | 0.3195 | 0.3270 | 0.1049 |
|
70 |
+
| 0.1652 | 11.76 | 6800 | 0.3080 | 0.3280 | 0.1056 |
|
71 |
+
| 0.1576 | 12.46 | 7200 | 0.2859 | 0.3218 | 0.1031 |
|
72 |
+
| 0.1558 | 13.15 | 7600 | 0.3143 | 0.3179 | 0.1018 |
|
73 |
+
| 0.1411 | 13.84 | 8000 | 0.3354 | 0.3171 | 0.1045 |
|
74 |
+
| 0.1411 | 14.53 | 8400 | 0.3285 | 0.3149 | 0.1018 |
|
75 |
+
| 0.1381 | 15.22 | 8800 | 0.3048 | 0.3138 | 0.1010 |
|
76 |
+
| 0.1178 | 15.92 | 9200 | 0.3421 | 0.3140 | 0.1012 |
|
77 |
+
| 0.1182 | 16.61 | 9600 | 0.3258 | 0.3109 | 0.1001 |
|
78 |
+
| 0.1131 | 17.3 | 10000 | 0.3220 | 0.3120 | 0.1002 |
|
79 |
+
| 0.1131 | 17.99 | 10400 | 0.3156 | 0.3098 | 0.0991 |
|
80 |
+
| 0.1031 | 18.69 | 10800 | 0.3198 | 0.3062 | 0.0980 |
|
81 |
+
| 0.1023 | 19.38 | 11200 | 0.3227 | 0.3021 | 0.0972 |
|
82 |
+
| 0.0959 | 20.07 | 11600 | 0.3187 | 0.3025 | 0.0973 |
|
83 |
+
| 0.0881 | 20.76 | 12000 | 0.3177 | 0.3004 | 0.0965 |
|
84 |
+
| 0.0881 | 21.45 | 12400 | 0.3435 | 0.2976 | 0.0960 |
|
85 |
+
| 0.0919 | 22.15 | 12800 | 0.3142 | 0.2958 | 0.0954 |
|
86 |
+
| 0.0787 | 22.84 | 13200 | 0.3010 | 0.3000 | 0.0970 |
|
87 |
+
| 0.0794 | 23.53 | 13600 | 0.3528 | 0.3008 | 0.0973 |
|
88 |
+
| 0.0751 | 24.22 | 14000 | 0.3352 | 0.2954 | 0.0961 |
|
89 |
+
| 0.0751 | 24.91 | 14400 | 0.3314 | 0.2977 | 0.0963 |
|
90 |
+
| 0.0778 | 25.61 | 14800 | 0.3214 | 0.2955 | 0.0953 |
|
91 |
+
| 0.0711 | 26.3 | 15200 | 0.3277 | 0.2936 | 0.0944 |
|
92 |
+
| 0.0681 | 26.99 | 15600 | 0.3237 | 0.2915 | 0.0940 |
|
93 |
+
| 0.0682 | 27.68 | 16000 | 0.3284 | 0.2918 | 0.0943 |
|
94 |
+
| 0.0682 | 28.37 | 16400 | 0.3304 | 0.2904 | 0.0933 |
|
95 |
+
| 0.0731 | 29.07 | 16800 | 0.3307 | 0.2881 | 0.0927 |
|
96 |
+
| 0.0619 | 29.76 | 17200 | 0.3293 | 0.2879 | 0.0927 |
|
97 |
+
|
98 |
+
|
99 |
+
### Framework versions
|
100 |
+
|
101 |
+
- Transformers 4.32.0.dev0
|
102 |
+
- Pytorch 2.0.1+cu118
|
103 |
+
- Datasets 1.18.3
|
104 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 0.1,
|
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_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": 0.075,
|
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": 29,
|
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": "4.32.0.dev0",
|
106 |
+
"use_weighted_layer_sum": false,
|
107 |
+
"vocab_size": 32,
|
108 |
+
"xvector_output_dim": 512
|
109 |
+
}
|
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 sha256:10513426a776859d1c335d1aa5eff465ef984c388caaeb1dd6c9d4ba5be6d319
|
3 |
+
size 1262033069
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0bce3ffac8d15ff015bb30f76361865cce76bacab2ad18c912392df5aa85be4
|
3 |
+
size 4027
|