End of training
Browse files- README.md +67 -0
- config.json +110 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Jun03_07-29-09_5cec47121b4a/events.out.tfevents.1717399790.5cec47121b4a.781.0 +3 -0
- runs/Jun03_07-32-24_5cec47121b4a/events.out.tfevents.1717399955.5cec47121b4a.781.1 +3 -0
- runs/Jun03_07-32-24_5cec47121b4a/events.out.tfevents.1717400901.5cec47121b4a.781.2 +3 -0
- runs/Jun03_08-02-23_5cec47121b4a/events.out.tfevents.1717401754.5cec47121b4a.781.3 +3 -0
- runs/Jun03_08-05-54_5cec47121b4a/events.out.tfevents.1717401967.5cec47121b4a.781.4 +3 -0
- runs/Jun03_08-11-36_5cec47121b4a/events.out.tfevents.1717402306.5cec47121b4a.781.5 +3 -0
- runs/Jun03_08-38-38_5cec47121b4a/events.out.tfevents.1717403939.5cec47121b4a.781.6 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- eng
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: facebook/wav2vec2-base-960h
|
6 |
+
tags:
|
7 |
+
- '[finetuned_model, lj_speech11]'
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- FYP/LJ-Speech1111
|
11 |
+
model-index:
|
12 |
+
- name: SpeechT5 STT Wav2Vec2
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# SpeechT5 STT Wav2Vec2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the Lj-Speech dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: nan
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0001
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 100
|
51 |
+
- num_epochs: 3
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 0.0 | 1.1277 | 53 | nan |
|
59 |
+
| 0.0 | 2.2553 | 106 | nan |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.41.2
|
65 |
+
- Pytorch 2.3.0+cu121
|
66 |
+
- Datasets 2.19.2
|
67 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
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": 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": "sum",
|
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_dropout": 0.0,
|
52 |
+
"feat_extract_norm": "group",
|
53 |
+
"feat_proj_dropout": 0.1,
|
54 |
+
"feat_quantizer_dropout": 0.0,
|
55 |
+
"final_dropout": 0.1,
|
56 |
+
"gradient_checkpointing": false,
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.1,
|
59 |
+
"hidden_dropout_prob": 0.1,
|
60 |
+
"hidden_size": 768,
|
61 |
+
"initializer_range": 0.02,
|
62 |
+
"intermediate_size": 3072,
|
63 |
+
"layer_norm_eps": 1e-05,
|
64 |
+
"layerdrop": 0.1,
|
65 |
+
"mask_feature_length": 10,
|
66 |
+
"mask_feature_min_masks": 0,
|
67 |
+
"mask_feature_prob": 0.0,
|
68 |
+
"mask_time_length": 10,
|
69 |
+
"mask_time_min_masks": 2,
|
70 |
+
"mask_time_prob": 0.05,
|
71 |
+
"model_type": "wav2vec2",
|
72 |
+
"num_adapter_layers": 3,
|
73 |
+
"num_attention_heads": 12,
|
74 |
+
"num_codevector_groups": 2,
|
75 |
+
"num_codevectors_per_group": 320,
|
76 |
+
"num_conv_pos_embedding_groups": 16,
|
77 |
+
"num_conv_pos_embeddings": 128,
|
78 |
+
"num_feat_extract_layers": 7,
|
79 |
+
"num_hidden_layers": 12,
|
80 |
+
"num_negatives": 100,
|
81 |
+
"output_hidden_size": 768,
|
82 |
+
"pad_token_id": 0,
|
83 |
+
"proj_codevector_dim": 256,
|
84 |
+
"tdnn_dilation": [
|
85 |
+
1,
|
86 |
+
2,
|
87 |
+
3,
|
88 |
+
1,
|
89 |
+
1
|
90 |
+
],
|
91 |
+
"tdnn_dim": [
|
92 |
+
512,
|
93 |
+
512,
|
94 |
+
512,
|
95 |
+
512,
|
96 |
+
1500
|
97 |
+
],
|
98 |
+
"tdnn_kernel": [
|
99 |
+
5,
|
100 |
+
3,
|
101 |
+
3,
|
102 |
+
1,
|
103 |
+
1
|
104 |
+
],
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.41.2",
|
107 |
+
"use_weighted_layer_sum": false,
|
108 |
+
"vocab_size": 32,
|
109 |
+
"xvector_output_dim": 512
|
110 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db199d38dd677248551a11622537efee70e5c2f384ce3df3b342d75eba77c06
|
3 |
+
size 377611120
|
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 |
+
}
|
runs/Jun03_07-29-09_5cec47121b4a/events.out.tfevents.1717399790.5cec47121b4a.781.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ab43c0f731ea7f69cf9bb83b39854f042518a6958d01ddd0e6478e6bd8b970b
|
3 |
+
size 6241
|
runs/Jun03_07-32-24_5cec47121b4a/events.out.tfevents.1717399955.5cec47121b4a.781.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f233caa882473a6f10e622b650217d8b5ef959f185fcd7d0e0f6da65e50ef823
|
3 |
+
size 6241
|
runs/Jun03_07-32-24_5cec47121b4a/events.out.tfevents.1717400901.5cec47121b4a.781.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61256894c9703b8d7bceed190d32c1b4a5d306ca50ad0a85232641a5bd524811
|
3 |
+
size 6241
|
runs/Jun03_08-02-23_5cec47121b4a/events.out.tfevents.1717401754.5cec47121b4a.781.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40a8a30767673fc4103503c580f7fb94238fcea9d7ef41b2a2e1e6ad5d7b6401
|
3 |
+
size 6241
|
runs/Jun03_08-05-54_5cec47121b4a/events.out.tfevents.1717401967.5cec47121b4a.781.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c45b9ead52c856ba6713fa711fcdf9fcda3f234d55213864001017a747f3a90
|
3 |
+
size 6241
|
runs/Jun03_08-11-36_5cec47121b4a/events.out.tfevents.1717402306.5cec47121b4a.781.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de5c25236101a413d3be72450c187f44efcc345feac384f908e520ab2b4cc07e
|
3 |
+
size 6241
|
runs/Jun03_08-38-38_5cec47121b4a/events.out.tfevents.1717403939.5cec47121b4a.781.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9fd59468387cfa6280b460d80b82bc26154f2a922e77b718b13108c203f82c1
|
3 |
+
size 14315
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f27f16df85037b23d8b7afc5f0ecd8816397670aeed96a8b00316bdc351167
|
3 |
+
size 5048
|