End of training
Browse files- README.md +88 -0
- config.json +118 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +1 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- vivos
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: working
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: vivos
|
18 |
+
type: vivos
|
19 |
+
config: default
|
20 |
+
split: None
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.1690242779130206
|
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 |
+
# working
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the vivos dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.2700
|
36 |
+
- Wer: 0.1690
|
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: 0.0001
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 64
|
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: 20
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
+
| 1.2111 | 2.0 | 292 | 0.9069 | 0.5315 |
|
72 |
+
| 0.6195 | 4.0 | 584 | 0.4762 | 0.3436 |
|
73 |
+
| 0.4338 | 6.0 | 876 | 0.3627 | 0.2657 |
|
74 |
+
| 0.3471 | 8.0 | 1168 | 0.4132 | 0.2817 |
|
75 |
+
| 0.2897 | 10.0 | 1460 | 0.3098 | 0.2178 |
|
76 |
+
| 0.2471 | 12.0 | 1752 | 0.2761 | 0.1957 |
|
77 |
+
| 0.2184 | 14.0 | 2044 | 0.2694 | 0.1807 |
|
78 |
+
| 0.1927 | 16.0 | 2336 | 0.2705 | 0.1753 |
|
79 |
+
| 0.1754 | 18.0 | 2628 | 0.2692 | 0.1709 |
|
80 |
+
| 0.1622 | 20.0 | 2920 | 0.2700 | 0.1690 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.42.3
|
86 |
+
- Pytorch 2.1.2
|
87 |
+
- Datasets 2.20.0
|
88 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.0,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
+
"mask_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 91,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.42.3",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 94,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e48d211eaeace563dc663cd882a1325341dec18b4cb922bb8b127d76f1f72e9
|
3 |
+
size 377801840
|
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 sha256:015bf27299727cb517cbd71351b1aa4b2c9d1baed92355839627001641b64d3b
|
3 |
+
size 5112
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"A": 1, "B": 2, "C": 3, "D": 4, "E": 5, "G": 6, "H": 7, "I": 8, "K": 9, "L": 10, "M": 11, "N": 12, "O": 13, "P": 14, "Q": 15, "R": 16, "S": 17, "T": 18, "U": 19, "V": 20, "X": 21, "Y": 22, "\u00c0": 23, "\u00c1": 24, "\u00c2": 25, "\u00c3": 26, "\u00c8": 27, "\u00c9": 28, "\u00ca": 29, "\u00cc": 30, "\u00cd": 31, "\u00d2": 32, "\u00d3": 33, "\u00d4": 34, "\u00d5": 35, "\u00d9": 36, "\u00da": 37, "\u00dd": 38, "\u0102": 39, "\u0110": 40, "\u0128": 41, "\u0168": 42, "\u01a0": 43, "\u01af": 44, "\u1ea0": 45, "\u1ea2": 46, "\u1ea4": 47, "\u1ea6": 48, "\u1ea8": 49, "\u1eaa": 50, "\u1eac": 51, "\u1eae": 52, "\u1eb0": 53, "\u1eb2": 54, "\u1eb4": 55, "\u1eb6": 56, "\u1eb8": 57, "\u1eba": 58, "\u1ebc": 59, "\u1ebe": 60, "\u1ec0": 61, "\u1ec2": 62, "\u1ec4": 63, "\u1ec6": 64, "\u1ec8": 65, "\u1eca": 66, "\u1ecc": 67, "\u1ece": 68, "\u1ed0": 69, "\u1ed2": 70, "\u1ed4": 71, "\u1ed6": 72, "\u1ed8": 73, "\u1eda": 74, "\u1edc": 75, "\u1ede": 76, "\u1ee0": 77, "\u1ee2": 78, "\u1ee4": 79, "\u1ee6": 80, "\u1ee8": 81, "\u1eea": 82, "\u1eec": 83, "\u1eee": 84, "\u1ef0": 85, "\u1ef2": 86, "\u1ef4": 87, "\u1ef6": 88, "\u1ef8": 89, "|": 0, "[UNK]": 90, "[PAD]": 91}
|