End of training
Browse files- README.md +113 -0
- config.json +117 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-large-xlsr-demo
|
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-large-xlsr-demo
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.6751
|
21 |
+
- Wer: 0.7846
|
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 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 1000
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
54 |
+
| 10.5108 | 0.5701 | 500 | 15.4314 | 1.0 |
|
55 |
+
| 5.61 | 1.1403 | 1000 | 11.3143 | 1.0 |
|
56 |
+
| 5.546 | 1.7104 | 1500 | 9.6388 | 1.0 |
|
57 |
+
| 5.1105 | 2.2805 | 2000 | 5.9376 | 1.0 |
|
58 |
+
| 4.9007 | 2.8506 | 2500 | 5.7582 | 1.0 |
|
59 |
+
| 4.5876 | 3.4208 | 3000 | 6.7190 | 1.0 |
|
60 |
+
| 4.3145 | 3.9909 | 3500 | 4.6527 | 1.0 |
|
61 |
+
| 3.5332 | 4.5610 | 4000 | 3.3622 | 1.0011 |
|
62 |
+
| 2.9071 | 5.1311 | 4500 | 2.7400 | 1.0176 |
|
63 |
+
| 2.5077 | 5.7013 | 5000 | 2.8219 | 0.9460 |
|
64 |
+
| 2.4145 | 6.2714 | 5500 | 2.4336 | 0.9570 |
|
65 |
+
| 2.2432 | 6.8415 | 6000 | 2.1500 | 0.9169 |
|
66 |
+
| 2.1376 | 7.4116 | 6500 | 2.1445 | 0.8930 |
|
67 |
+
| 2.0841 | 7.9818 | 7000 | 2.1312 | 0.8864 |
|
68 |
+
| 1.8288 | 8.5519 | 7500 | 1.9040 | 0.8728 |
|
69 |
+
| 1.6863 | 9.1220 | 8000 | 1.8913 | 0.8434 |
|
70 |
+
| 1.7453 | 9.6921 | 8500 | 2.1214 | 0.8507 |
|
71 |
+
| 1.6896 | 10.2623 | 9000 | 1.8329 | 0.8548 |
|
72 |
+
| 1.6063 | 10.8324 | 9500 | 1.8248 | 0.8386 |
|
73 |
+
| 1.3838 | 11.4025 | 10000 | 1.7811 | 0.8379 |
|
74 |
+
| 1.5255 | 11.9726 | 10500 | 2.3148 | 0.8390 |
|
75 |
+
| 1.4269 | 12.5428 | 11000 | 2.1530 | 0.8184 |
|
76 |
+
| 1.3452 | 13.1129 | 11500 | 1.7208 | 0.8221 |
|
77 |
+
| 1.35 | 13.6830 | 12000 | 1.8269 | 0.8290 |
|
78 |
+
| 1.3656 | 14.2531 | 12500 | 1.6902 | 0.8313 |
|
79 |
+
| 1.2036 | 14.8233 | 13000 | 2.0816 | 0.8206 |
|
80 |
+
| 1.2144 | 15.3934 | 13500 | 1.7623 | 0.8103 |
|
81 |
+
| 1.1648 | 15.9635 | 14000 | 1.7197 | 0.8154 |
|
82 |
+
| 1.1341 | 16.5336 | 14500 | 1.7560 | 0.8110 |
|
83 |
+
| 1.0716 | 17.1038 | 15000 | 1.7750 | 0.8099 |
|
84 |
+
| 1.1187 | 17.6739 | 15500 | 1.7946 | 0.8180 |
|
85 |
+
| 1.0633 | 18.2440 | 16000 | 1.7877 | 0.7996 |
|
86 |
+
| 1.0069 | 18.8141 | 16500 | 1.8482 | 0.8243 |
|
87 |
+
| 0.9703 | 19.3843 | 17000 | 1.6073 | 0.7960 |
|
88 |
+
| 1.0122 | 19.9544 | 17500 | 1.7191 | 0.8099 |
|
89 |
+
| 0.9993 | 20.5245 | 18000 | 1.7208 | 0.7956 |
|
90 |
+
| 0.9861 | 21.0946 | 18500 | 1.6628 | 0.7949 |
|
91 |
+
| 0.9621 | 21.6648 | 19000 | 1.7685 | 0.7930 |
|
92 |
+
| 0.8936 | 22.2349 | 19500 | 1.7232 | 0.8026 |
|
93 |
+
| 0.888 | 22.8050 | 20000 | 1.7204 | 0.8015 |
|
94 |
+
| 0.9027 | 23.3751 | 20500 | 1.7844 | 0.7923 |
|
95 |
+
| 0.8808 | 23.9453 | 21000 | 1.7159 | 0.7945 |
|
96 |
+
| 0.8652 | 24.5154 | 21500 | 1.6887 | 0.7934 |
|
97 |
+
| 0.7545 | 25.0855 | 22000 | 1.6633 | 0.7937 |
|
98 |
+
| 0.7664 | 25.6556 | 22500 | 1.6745 | 0.7919 |
|
99 |
+
| 0.7518 | 26.2258 | 23000 | 1.7122 | 0.7930 |
|
100 |
+
| 0.8475 | 26.7959 | 23500 | 1.6901 | 0.7868 |
|
101 |
+
| 0.7527 | 27.3660 | 24000 | 1.6937 | 0.7835 |
|
102 |
+
| 0.7531 | 27.9361 | 24500 | 1.6835 | 0.7820 |
|
103 |
+
| 0.7686 | 28.5063 | 25000 | 1.6734 | 0.7901 |
|
104 |
+
| 0.7525 | 29.0764 | 25500 | 1.6766 | 0.7868 |
|
105 |
+
| 0.7765 | 29.6465 | 26000 | 1.6751 | 0.7846 |
|
106 |
+
|
107 |
+
|
108 |
+
### Framework versions
|
109 |
+
|
110 |
+
- Transformers 4.41.2
|
111 |
+
- Pytorch 2.3.0
|
112 |
+
- Datasets 2.19.2
|
113 |
+
- Tokenizers 0.19.1
|
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": 0.0,
|
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": 0.05,
|
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": 1795,
|
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": "4.41.2",
|
114 |
+
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 1798,
|
116 |
+
"xvector_output_dim": 512
|
117 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f47f3c1983d36e0f2a770863f3f66434cbc3f93847fa65728b12945ab1d1419
|
3 |
+
size 1269179304
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed80096d79b2a970dabf27215de4e699424f008cf8c0a579f5431ce8a89e5673
|
3 |
+
size 5048
|