anjulRajendraSharma
commited on
Commit
•
ab5465e
1
Parent(s):
31858f4
upload model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +70 -0
- added_tokens.json +1 -0
- all_results.json +14 -0
- checkpoint-2500/config.json +121 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/preprocessor_config.json +9 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +0 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-3000/config.json +121 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/preprocessor_config.json +9 -0
- checkpoint-3000/pytorch_model.bin +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/trainer_state.json +0 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-3500/config.json +121 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/preprocessor_config.json +9 -0
- checkpoint-3500/pytorch_model.bin +3 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/trainer_state.json +0 -0
- checkpoint-3500/training_args.bin +3 -0
- config.json +121 -0
- eval_results.json +9 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Jan28_04-48-55_d2987f7d2cf0/1643345395.002263/events.out.tfevents.1643345395.d2987f7d2cf0.1792174.1 +3 -0
- runs/Jan28_04-48-55_d2987f7d2cf0/events.out.tfevents.1643345394.d2987f7d2cf0.1792174.0 +3 -0
- runs/Jan28_15-46-12_d2987f7d2cf0/1643384837.416991/events.out.tfevents.1643384837.d2987f7d2cf0.2385063.1 +3 -0
- runs/Jan28_15-46-12_d2987f7d2cf0/events.out.tfevents.1643384837.d2987f7d2cf0.2385063.0 +3 -0
- runs/Jan28_15-52-48_d2987f7d2cf0/1643385218.1226718/events.out.tfevents.1643385218.d2987f7d2cf0.2386553.1 +3 -0
- runs/Jan28_15-52-48_d2987f7d2cf0/events.out.tfevents.1643385218.d2987f7d2cf0.2386553.0 +3 -0
- runs/Jan28_16-07-07_d2987f7d2cf0/1643386076.9584827/events.out.tfevents.1643386076.d2987f7d2cf0.2386872.1 +3 -0
- runs/Jan28_16-07-07_d2987f7d2cf0/events.out.tfevents.1643386076.d2987f7d2cf0.2386872.0 +3 -0
- runs/Jan28_16-12-12_d2987f7d2cf0/1643386381.6106/events.out.tfevents.1643386381.d2987f7d2cf0.2388587.1 +3 -0
- runs/Jan28_16-12-12_d2987f7d2cf0/events.out.tfevents.1643386381.d2987f7d2cf0.2388587.0 +3 -0
- runs/Jan28_16-12-12_d2987f7d2cf0/events.out.tfevents.1643386687.d2987f7d2cf0.2388587.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- automatic-speech-recognition
|
4 |
+
- librispeech_asr
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: wavlm-libri-clean-100h-base
|
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 |
+
# wavlm-libri-clean-100h-base
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on the LIBRISPEECH_ASR - CLEAN dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0955
|
19 |
+
- Wer: 0.0773
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0003
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 1.0
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
52 |
+
| 2.8664 | 0.17 | 300 | 2.8439 | 1.0 |
|
53 |
+
| 0.5009 | 0.34 | 600 | 0.2709 | 0.2162 |
|
54 |
+
| 0.2056 | 0.5 | 900 | 0.1934 | 0.1602 |
|
55 |
+
| 0.1648 | 0.67 | 1200 | 0.1576 | 0.1306 |
|
56 |
+
| 0.1922 | 0.84 | 1500 | 0.1358 | 0.1114 |
|
57 |
+
| 0.093 | 1.01 | 1800 | 0.1277 | 0.1035 |
|
58 |
+
| 0.0652 | 1.18 | 2100 | 0.1251 | 0.1005 |
|
59 |
+
| 0.0848 | 1.35 | 2400 | 0.1188 | 0.0964 |
|
60 |
+
| 0.0706 | 1.51 | 2700 | 0.1091 | 0.0905 |
|
61 |
+
| 0.0846 | 1.68 | 3000 | 0.1018 | 0.0840 |
|
62 |
+
| 0.0684 | 1.85 | 3300 | 0.0978 | 0.0809 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.15.0
|
68 |
+
- Pytorch 1.9.1
|
69 |
+
- Datasets 1.18.0
|
70 |
+
- Tokenizers 0.10.3
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 29, "</s>": 30}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.96,
|
3 |
+
"eval_loss": 0.09545929729938507,
|
4 |
+
"eval_runtime": 297.6826,
|
5 |
+
"eval_samples": 2642,
|
6 |
+
"eval_samples_per_second": 8.875,
|
7 |
+
"eval_steps_per_second": 0.558,
|
8 |
+
"eval_wer": 0.07727092423641412,
|
9 |
+
"train_loss": 0.0,
|
10 |
+
"train_runtime": 7.6753,
|
11 |
+
"train_samples": 28538,
|
12 |
+
"train_samples_per_second": 3718.173,
|
13 |
+
"train_steps_per_second": 232.435
|
14 |
+
}
|
checkpoint-2500/config.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/wavlm-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"WavLMForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 256,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": false,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": false,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_norm": "group",
|
51 |
+
"feat_proj_dropout": 0.0,
|
52 |
+
"feat_quantizer_dropout": 0.0,
|
53 |
+
"final_dropout": 0.0,
|
54 |
+
"freeze_feat_extract_train": true,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 768,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_channel_length": 10,
|
63 |
+
"mask_channel_min_space": 1,
|
64 |
+
"mask_channel_other": 0.0,
|
65 |
+
"mask_channel_prob": 0.0,
|
66 |
+
"mask_channel_selection": "static",
|
67 |
+
"mask_feature_length": 10,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.0,
|
70 |
+
"mask_time_length": 10,
|
71 |
+
"mask_time_min_masks": 2,
|
72 |
+
"mask_time_min_space": 1,
|
73 |
+
"mask_time_other": 0.0,
|
74 |
+
"mask_time_prob": 0.05,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"max_bucket_distance": 800,
|
77 |
+
"model_type": "wavlm",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_buckets": 320,
|
83 |
+
"num_codevector_groups": 2,
|
84 |
+
"num_codevectors_per_group": 320,
|
85 |
+
"num_conv_pos_embedding_groups": 16,
|
86 |
+
"num_conv_pos_embeddings": 128,
|
87 |
+
"num_ctc_classes": 80,
|
88 |
+
"num_feat_extract_layers": 7,
|
89 |
+
"num_hidden_layers": 12,
|
90 |
+
"num_negatives": 100,
|
91 |
+
"output_hidden_size": 768,
|
92 |
+
"pad_token_id": 28,
|
93 |
+
"proj_codevector_dim": 256,
|
94 |
+
"tdnn_dilation": [
|
95 |
+
1,
|
96 |
+
2,
|
97 |
+
3,
|
98 |
+
1,
|
99 |
+
1
|
100 |
+
],
|
101 |
+
"tdnn_dim": [
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
512,
|
105 |
+
512,
|
106 |
+
1500
|
107 |
+
],
|
108 |
+
"tdnn_kernel": [
|
109 |
+
5,
|
110 |
+
3,
|
111 |
+
3,
|
112 |
+
1,
|
113 |
+
1
|
114 |
+
],
|
115 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
116 |
+
"torch_dtype": "float32",
|
117 |
+
"transformers_version": "4.15.0",
|
118 |
+
"use_weighted_layer_sum": false,
|
119 |
+
"vocab_size": 31,
|
120 |
+
"xvector_output_dim": 512
|
121 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fb791143dfbb3b1cf1d14e46d62e481c6e2c78ea34af1bf60acc3c3e01cc95c
|
3 |
+
size 721780605
|
checkpoint-2500/preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
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 |
+
}
|
checkpoint-2500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a18ea5c1191e01820b5482ebe5e73a366dc76e3747a08a397f2ac22a13895cf5
|
3 |
+
size 377719629
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff66da33640d4a701404dc80c65deb581e473dc3806f2431e25e6d869a16613
|
3 |
+
size 17563
|
checkpoint-2500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d7885acd14de8af3583d1c613c429fcc523623c0fbb1d5873894df5cfccd602
|
3 |
+
size 559
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:addfb91bf467aca28586b06bb3086e02b38295375b6e572a9817c013856b8ef7
|
3 |
+
size 623
|
checkpoint-2500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ac8ac9c168668ea9d4f2d6887a03ad67003a09c72bd20b80b257e71770101f
|
3 |
+
size 2991
|
checkpoint-3000/config.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/wavlm-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"WavLMForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 256,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": false,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": false,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_norm": "group",
|
51 |
+
"feat_proj_dropout": 0.0,
|
52 |
+
"feat_quantizer_dropout": 0.0,
|
53 |
+
"final_dropout": 0.0,
|
54 |
+
"freeze_feat_extract_train": true,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 768,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_channel_length": 10,
|
63 |
+
"mask_channel_min_space": 1,
|
64 |
+
"mask_channel_other": 0.0,
|
65 |
+
"mask_channel_prob": 0.0,
|
66 |
+
"mask_channel_selection": "static",
|
67 |
+
"mask_feature_length": 10,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.0,
|
70 |
+
"mask_time_length": 10,
|
71 |
+
"mask_time_min_masks": 2,
|
72 |
+
"mask_time_min_space": 1,
|
73 |
+
"mask_time_other": 0.0,
|
74 |
+
"mask_time_prob": 0.05,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"max_bucket_distance": 800,
|
77 |
+
"model_type": "wavlm",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_buckets": 320,
|
83 |
+
"num_codevector_groups": 2,
|
84 |
+
"num_codevectors_per_group": 320,
|
85 |
+
"num_conv_pos_embedding_groups": 16,
|
86 |
+
"num_conv_pos_embeddings": 128,
|
87 |
+
"num_ctc_classes": 80,
|
88 |
+
"num_feat_extract_layers": 7,
|
89 |
+
"num_hidden_layers": 12,
|
90 |
+
"num_negatives": 100,
|
91 |
+
"output_hidden_size": 768,
|
92 |
+
"pad_token_id": 28,
|
93 |
+
"proj_codevector_dim": 256,
|
94 |
+
"tdnn_dilation": [
|
95 |
+
1,
|
96 |
+
2,
|
97 |
+
3,
|
98 |
+
1,
|
99 |
+
1
|
100 |
+
],
|
101 |
+
"tdnn_dim": [
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
512,
|
105 |
+
512,
|
106 |
+
1500
|
107 |
+
],
|
108 |
+
"tdnn_kernel": [
|
109 |
+
5,
|
110 |
+
3,
|
111 |
+
3,
|
112 |
+
1,
|
113 |
+
1
|
114 |
+
],
|
115 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
116 |
+
"torch_dtype": "float32",
|
117 |
+
"transformers_version": "4.15.0",
|
118 |
+
"use_weighted_layer_sum": false,
|
119 |
+
"vocab_size": 31,
|
120 |
+
"xvector_output_dim": 512
|
121 |
+
}
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7495ea2d4207f8ff07a18a9aa6ce6c38a13c4962eec5355b1a81fbdf8f37c8c7
|
3 |
+
size 721780605
|
checkpoint-3000/preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
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 |
+
}
|
checkpoint-3000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2259d6b6a9a2ecdafb79c75724a6b769fb07230e7959bd0aa8f8527069d58524
|
3 |
+
size 377719629
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e57e0ea02d5be7051bebc2ee12a6143a760a7dbb68d231c38f991a53c5f5fa2
|
3 |
+
size 17627
|
checkpoint-3000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:093dbaa048280b9a3992fd16ffeff174077217d2aa672399db12a99b1447ff0e
|
3 |
+
size 559
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aa567110332372f26c1efc0590179f8f95f00ec7e01e1691c668f64711cafc3
|
3 |
+
size 623
|
checkpoint-3000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ac8ac9c168668ea9d4f2d6887a03ad67003a09c72bd20b80b257e71770101f
|
3 |
+
size 2991
|
checkpoint-3500/config.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/wavlm-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"WavLMForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 256,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": false,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": false,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_norm": "group",
|
51 |
+
"feat_proj_dropout": 0.0,
|
52 |
+
"feat_quantizer_dropout": 0.0,
|
53 |
+
"final_dropout": 0.0,
|
54 |
+
"freeze_feat_extract_train": true,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 768,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_channel_length": 10,
|
63 |
+
"mask_channel_min_space": 1,
|
64 |
+
"mask_channel_other": 0.0,
|
65 |
+
"mask_channel_prob": 0.0,
|
66 |
+
"mask_channel_selection": "static",
|
67 |
+
"mask_feature_length": 10,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.0,
|
70 |
+
"mask_time_length": 10,
|
71 |
+
"mask_time_min_masks": 2,
|
72 |
+
"mask_time_min_space": 1,
|
73 |
+
"mask_time_other": 0.0,
|
74 |
+
"mask_time_prob": 0.05,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"max_bucket_distance": 800,
|
77 |
+
"model_type": "wavlm",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_buckets": 320,
|
83 |
+
"num_codevector_groups": 2,
|
84 |
+
"num_codevectors_per_group": 320,
|
85 |
+
"num_conv_pos_embedding_groups": 16,
|
86 |
+
"num_conv_pos_embeddings": 128,
|
87 |
+
"num_ctc_classes": 80,
|
88 |
+
"num_feat_extract_layers": 7,
|
89 |
+
"num_hidden_layers": 12,
|
90 |
+
"num_negatives": 100,
|
91 |
+
"output_hidden_size": 768,
|
92 |
+
"pad_token_id": 28,
|
93 |
+
"proj_codevector_dim": 256,
|
94 |
+
"tdnn_dilation": [
|
95 |
+
1,
|
96 |
+
2,
|
97 |
+
3,
|
98 |
+
1,
|
99 |
+
1
|
100 |
+
],
|
101 |
+
"tdnn_dim": [
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
512,
|
105 |
+
512,
|
106 |
+
1500
|
107 |
+
],
|
108 |
+
"tdnn_kernel": [
|
109 |
+
5,
|
110 |
+
3,
|
111 |
+
3,
|
112 |
+
1,
|
113 |
+
1
|
114 |
+
],
|
115 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
116 |
+
"torch_dtype": "float32",
|
117 |
+
"transformers_version": "4.15.0",
|
118 |
+
"use_weighted_layer_sum": false,
|
119 |
+
"vocab_size": 31,
|
120 |
+
"xvector_output_dim": 512
|
121 |
+
}
|
checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a84dbc7ec17c35e0eb9855ae267a22d87d23d66b1823b63ab4ec51920f19ebe4
|
3 |
+
size 721780605
|
checkpoint-3500/preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
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 |
+
}
|
checkpoint-3500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee9330b00c16a2b30f23e09ecc63408058e193e50d7838447c1c87a0bc9f0c52
|
3 |
+
size 377719629
|
checkpoint-3500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a15658bb0935e17efb513e7b6f3d84ee2fd4fb12aac29d62200444ab6afa890b
|
3 |
+
size 17627
|
checkpoint-3500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b853338b3fe0587db6bc86d6a7c83b41072523465a2431483252763bf4fe51a
|
3 |
+
size 559
|
checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f83b5b46a684f6ed4abd343a4042beecee67985c8385de39e6b1490461106d
|
3 |
+
size 623
|
checkpoint-3500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ac8ac9c168668ea9d4f2d6887a03ad67003a09c72bd20b80b257e71770101f
|
3 |
+
size 2991
|
config.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/wavlm-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"WavLMForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 256,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": false,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": false,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_norm": "group",
|
51 |
+
"feat_proj_dropout": 0.0,
|
52 |
+
"feat_quantizer_dropout": 0.0,
|
53 |
+
"final_dropout": 0.0,
|
54 |
+
"freeze_feat_extract_train": true,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 768,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_channel_length": 10,
|
63 |
+
"mask_channel_min_space": 1,
|
64 |
+
"mask_channel_other": 0.0,
|
65 |
+
"mask_channel_prob": 0.0,
|
66 |
+
"mask_channel_selection": "static",
|
67 |
+
"mask_feature_length": 10,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.0,
|
70 |
+
"mask_time_length": 10,
|
71 |
+
"mask_time_min_masks": 2,
|
72 |
+
"mask_time_min_space": 1,
|
73 |
+
"mask_time_other": 0.0,
|
74 |
+
"mask_time_prob": 0.05,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"max_bucket_distance": 800,
|
77 |
+
"model_type": "wavlm",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_buckets": 320,
|
83 |
+
"num_codevector_groups": 2,
|
84 |
+
"num_codevectors_per_group": 320,
|
85 |
+
"num_conv_pos_embedding_groups": 16,
|
86 |
+
"num_conv_pos_embeddings": 128,
|
87 |
+
"num_ctc_classes": 80,
|
88 |
+
"num_feat_extract_layers": 7,
|
89 |
+
"num_hidden_layers": 12,
|
90 |
+
"num_negatives": 100,
|
91 |
+
"output_hidden_size": 768,
|
92 |
+
"pad_token_id": 28,
|
93 |
+
"proj_codevector_dim": 256,
|
94 |
+
"tdnn_dilation": [
|
95 |
+
1,
|
96 |
+
2,
|
97 |
+
3,
|
98 |
+
1,
|
99 |
+
1
|
100 |
+
],
|
101 |
+
"tdnn_dim": [
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
512,
|
105 |
+
512,
|
106 |
+
1500
|
107 |
+
],
|
108 |
+
"tdnn_kernel": [
|
109 |
+
5,
|
110 |
+
3,
|
111 |
+
3,
|
112 |
+
1,
|
113 |
+
1
|
114 |
+
],
|
115 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
116 |
+
"torch_dtype": "float32",
|
117 |
+
"transformers_version": "4.15.0",
|
118 |
+
"use_weighted_layer_sum": false,
|
119 |
+
"vocab_size": 31,
|
120 |
+
"xvector_output_dim": 512
|
121 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.96,
|
3 |
+
"eval_loss": 0.09545929729938507,
|
4 |
+
"eval_runtime": 297.6826,
|
5 |
+
"eval_samples": 2642,
|
6 |
+
"eval_samples_per_second": 8.875,
|
7 |
+
"eval_steps_per_second": 0.558,
|
8 |
+
"eval_wer": 0.07727092423641412
|
9 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
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:ee9330b00c16a2b30f23e09ecc63408058e193e50d7838447c1c87a0bc9f0c52
|
3 |
+
size 377719629
|
runs/Jan28_04-48-55_d2987f7d2cf0/1643345395.002263/events.out.tfevents.1643345395.d2987f7d2cf0.1792174.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:752f881e0df06e3a56214f5e330f5becc9539b54ab480a80ff6480bfd9907a7e
|
3 |
+
size 4784
|
runs/Jan28_04-48-55_d2987f7d2cf0/events.out.tfevents.1643345394.d2987f7d2cf0.1792174.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94db18774842b14dccc30f96f1106f980c2650c1e75a1e2bd0ad3385c6df6a51
|
3 |
+
size 585230
|
runs/Jan28_15-46-12_d2987f7d2cf0/1643384837.416991/events.out.tfevents.1643384837.d2987f7d2cf0.2385063.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d4fcf9aeb6de595206114cf09c7ba14feb8ac4ec76f3e265db909d17e9ccde1
|
3 |
+
size 4784
|
runs/Jan28_15-46-12_d2987f7d2cf0/events.out.tfevents.1643384837.d2987f7d2cf0.2385063.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d18a32cf6885d879ed343a8460fbfc114a145e1303b7218da2e19782e9c6678
|
3 |
+
size 7290
|
runs/Jan28_15-52-48_d2987f7d2cf0/1643385218.1226718/events.out.tfevents.1643385218.d2987f7d2cf0.2386553.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72c57ccb1341a2be27b031be484ba4475f953003e25ed94fa4300305541f80ab
|
3 |
+
size 4784
|
runs/Jan28_15-52-48_d2987f7d2cf0/events.out.tfevents.1643385218.d2987f7d2cf0.2386553.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6fba388c2f20fb8ee64278a063e39e787102e19fe10f11cce935eb6ae394626
|
3 |
+
size 5135
|
runs/Jan28_16-07-07_d2987f7d2cf0/1643386076.9584827/events.out.tfevents.1643386076.d2987f7d2cf0.2386872.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e21ce31da8c61a13df25e95852ce667438a496a94af0f95f1feafb1cb3767e5
|
3 |
+
size 4784
|
runs/Jan28_16-07-07_d2987f7d2cf0/events.out.tfevents.1643386076.d2987f7d2cf0.2386872.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea03685519d38aedc95d42b2abe61225d14c91dc6227e52d7fa22db6c202d35
|
3 |
+
size 7489
|
runs/Jan28_16-12-12_d2987f7d2cf0/1643386381.6106/events.out.tfevents.1643386381.d2987f7d2cf0.2388587.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:167a167f20cd827b216614aba78a1dc43407d32ce19bf6ed426be73cfd87e21d
|
3 |
+
size 4784
|
runs/Jan28_16-12-12_d2987f7d2cf0/events.out.tfevents.1643386381.d2987f7d2cf0.2388587.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:344870ca309d912e401fb72795fcf15744de1ca54ba275d7b263cfbb437c1778
|
3 |
+
size 5488
|
runs/Jan28_16-12-12_d2987f7d2cf0/events.out.tfevents.1643386687.d2987f7d2cf0.2388587.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:671838c8481001a2572b25babbe8de1075e800c5de8699537ec4f0c2cf547d41
|
3 |
+
size 358
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wavlm-libri-clean-100h-base", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.96,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 7.6753,
|
5 |
+
"train_samples": 28538,
|
6 |
+
"train_samples_per_second": 3718.173,
|
7 |
+
"train_steps_per_second": 232.435
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04b72fe215fc52f9c23c9f56ceb93f9b5f3d0dce3528061f5506af12028642c
|
3 |
+
size 2991
|