arslanarjumand
commited on
Commit
•
138e521
1
Parent(s):
08f9983
arslanarjumand/wav2vec-read-aloud
Browse files- README.md +70 -0
- config.json +94 -0
- model.safetensors +3 -0
- preprocessor_config.json +11 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: facebook/w2v-bert-2.0
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: wav2vec-read_aloud
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# wav2vec-read_aloud
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 973.4864
|
19 |
+
- Pcc Accuracy: 0.7547
|
20 |
+
- Pcc Fluency: 0.7664
|
21 |
+
- Pcc Total Score: 0.8143
|
22 |
+
- Pcc Content: nan
|
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: 5.5e-05
|
42 |
+
- train_batch_size: 2
|
43 |
+
- eval_batch_size: 6
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 12
|
46 |
+
- total_train_batch_size: 24
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_ratio: 0.4
|
50 |
+
- num_epochs: 15
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------:|:---------------:|:-----------:|
|
56 |
+
| 2390.3109 | 1.95 | 500 | 2342.6951 | nan | 0.4815 | nan | nan |
|
57 |
+
| 2164.6891 | 3.9 | 1000 | 2318.7217 | nan | 0.6461 | nan | nan |
|
58 |
+
| 1078.8019 | 5.85 | 1500 | 1029.2085 | 0.6188 | 0.7014 | 0.6845 | nan |
|
59 |
+
| 974.6556 | 7.8 | 2000 | 985.5543 | 0.7117 | 0.7355 | 0.7743 | nan |
|
60 |
+
| 1002.623 | 9.75 | 2500 | 989.1628 | 0.7401 | 0.7533 | 0.7995 | nan |
|
61 |
+
| 947.5643 | 11.7 | 3000 | 972.3806 | 0.7507 | 0.7628 | 0.8103 | nan |
|
62 |
+
| 995.6286 | 13.65 | 3500 | 973.4864 | 0.7547 | 0.7664 | 0.8143 | nan |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.37.0
|
68 |
+
- Pytorch 2.1.2
|
69 |
+
- Datasets 2.18.0
|
70 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.006,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertForSequenceClassification"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0094,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 128,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "sum",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.0005,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.004,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1",
|
33 |
+
"2": "LABEL_2",
|
34 |
+
"3": "LABEL_3"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 4096,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3
|
43 |
+
},
|
44 |
+
"layer_norm_eps": 1e-05,
|
45 |
+
"layerdrop": 0.0005,
|
46 |
+
"left_max_position_embeddings": 64,
|
47 |
+
"mask_feature_length": 5,
|
48 |
+
"mask_feature_min_masks": 5,
|
49 |
+
"mask_feature_prob": 0.0575,
|
50 |
+
"mask_time_length": 5,
|
51 |
+
"mask_time_min_masks": 5,
|
52 |
+
"mask_time_prob": 0.0585,
|
53 |
+
"max_source_positions": 5000,
|
54 |
+
"model_type": "wav2vec2-bert",
|
55 |
+
"num_adapter_layers": 1,
|
56 |
+
"num_attention_heads": 16,
|
57 |
+
"num_codevector_groups": 2,
|
58 |
+
"num_codevectors_per_group": 320,
|
59 |
+
"num_hidden_layers": 12,
|
60 |
+
"num_negatives": 100,
|
61 |
+
"output_hidden_size": 1024,
|
62 |
+
"pad_token_id": 0,
|
63 |
+
"position_embeddings_type": "relative_key",
|
64 |
+
"proj_codevector_dim": 768,
|
65 |
+
"right_max_position_embeddings": 8,
|
66 |
+
"rotary_embedding_base": 10000,
|
67 |
+
"tdnn_dilation": [
|
68 |
+
1,
|
69 |
+
2,
|
70 |
+
3,
|
71 |
+
1,
|
72 |
+
1
|
73 |
+
],
|
74 |
+
"tdnn_dim": [
|
75 |
+
512,
|
76 |
+
512,
|
77 |
+
512,
|
78 |
+
512,
|
79 |
+
1500
|
80 |
+
],
|
81 |
+
"tdnn_kernel": [
|
82 |
+
5,
|
83 |
+
3,
|
84 |
+
3,
|
85 |
+
1,
|
86 |
+
1
|
87 |
+
],
|
88 |
+
"torch_dtype": "float32",
|
89 |
+
"transformers_version": "4.37.0",
|
90 |
+
"use_intermediate_ffn_before_adapter": false,
|
91 |
+
"use_weighted_layer_sum": false,
|
92 |
+
"vocab_size": null,
|
93 |
+
"xvector_output_dim": 512
|
94 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4660acd2a4de557833aa1ce4fbd7ab93333e7c01cf645ab396a4e3a220db11a
|
3 |
+
size 1206994592
|
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
3 |
+
"feature_size": 80,
|
4 |
+
"num_mel_bins": 80,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 1,
|
7 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000,
|
10 |
+
"stride": 2
|
11 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:596191023888232fe0a588808a22c46817c7b68e607063d9fa88732a803e892a
|
3 |
+
size 4728
|