End of training
Browse files- README.md +108 -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 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice_13_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: output
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice_13_0
|
18 |
+
type: common_voice_13_0
|
19 |
+
config: hi
|
20 |
+
split: test
|
21 |
+
args: hi
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 1.019918009027289
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# output
|
32 |
+
|
33 |
+
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_13_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.7883
|
36 |
+
- Wer: 1.0199
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0003
|
56 |
+
- train_batch_size: 2
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 8
|
60 |
+
- total_train_batch_size: 16
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 30
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
70 |
+
| 5.92 | 0.95 | 400 | 2.9522 | 1.0026 |
|
71 |
+
| 1.0435 | 1.89 | 800 | 0.8608 | 1.0552 |
|
72 |
+
| 0.5354 | 2.84 | 1200 | 0.7762 | 1.0169 |
|
73 |
+
| 0.404 | 3.79 | 1600 | 0.6984 | 1.0293 |
|
74 |
+
| 0.3301 | 4.73 | 2000 | 0.6811 | 1.0217 |
|
75 |
+
| 0.2745 | 5.68 | 2400 | 0.7027 | 1.0308 |
|
76 |
+
| 0.2346 | 6.63 | 2800 | 0.7296 | 1.0185 |
|
77 |
+
| 0.2096 | 7.57 | 3200 | 0.7148 | 1.0294 |
|
78 |
+
| 0.1912 | 8.52 | 3600 | 0.7109 | 1.0335 |
|
79 |
+
| 0.172 | 9.47 | 4000 | 0.7894 | 1.0252 |
|
80 |
+
| 0.1567 | 10.41 | 4400 | 0.7592 | 1.0219 |
|
81 |
+
| 0.1457 | 11.36 | 4800 | 0.8030 | 1.0141 |
|
82 |
+
| 0.1337 | 12.31 | 5200 | 0.7811 | 1.0237 |
|
83 |
+
| 0.1288 | 13.25 | 5600 | 0.7703 | 1.0188 |
|
84 |
+
| 0.1165 | 14.2 | 6000 | 0.7728 | 1.0199 |
|
85 |
+
| 0.105 | 15.15 | 6400 | 0.7934 | 1.0206 |
|
86 |
+
| 0.1028 | 16.09 | 6800 | 0.7978 | 1.0185 |
|
87 |
+
| 0.092 | 17.04 | 7200 | 0.8276 | 1.0289 |
|
88 |
+
| 0.0901 | 17.99 | 7600 | 0.7881 | 1.0202 |
|
89 |
+
| 0.0818 | 18.93 | 8000 | 0.7847 | 1.0162 |
|
90 |
+
| 0.0801 | 19.88 | 8400 | 0.8142 | 1.0230 |
|
91 |
+
| 0.0768 | 20.83 | 8800 | 0.7735 | 1.0215 |
|
92 |
+
| 0.0721 | 21.78 | 9200 | 0.7941 | 1.0227 |
|
93 |
+
| 0.0658 | 22.72 | 9600 | 0.8100 | 1.0219 |
|
94 |
+
| 0.0627 | 23.67 | 10000 | 0.7592 | 1.0196 |
|
95 |
+
| 0.0591 | 24.62 | 10400 | 0.8028 | 1.0210 |
|
96 |
+
| 0.0537 | 25.56 | 10800 | 0.8019 | 1.0253 |
|
97 |
+
| 0.0507 | 26.51 | 11200 | 0.7951 | 1.0212 |
|
98 |
+
| 0.0495 | 27.46 | 11600 | 0.7893 | 1.0207 |
|
99 |
+
| 0.0466 | 28.4 | 12000 | 0.7854 | 1.0188 |
|
100 |
+
| 0.0431 | 29.35 | 12400 | 0.7883 | 1.0199 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.32.1
|
106 |
+
- Pytorch 2.2.0+cu121
|
107 |
+
- Datasets 2.12.0
|
108 |
+
- Tokenizers 0.13.2
|
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": 0.0,
|
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": 100,
|
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": "4.32.1",
|
106 |
+
"use_weighted_layer_sum": false,
|
107 |
+
"vocab_size": 102,
|
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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24c2429c7148cb6f3d7db960bd0db87b4a02593fd8efa7465446c88dd917eaf6
|
3 |
+
size 1262320554
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:151ceed9b3e926e02a9ab2312f33ff4816de2fa220db7dc87f19b2f110c7c22e
|
3 |
+
size 4408
|