patrickvonplaten
commited on
Commit
•
3f312b0
1
Parent(s):
574a86c
up
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +71 -0
- added_tokens.json +1 -0
- all_results.json +14 -0
- checkpoint-1500/config.json +99 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/preprocessor_config.json +9 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/rng_state_0.pth +3 -0
- checkpoint-1500/rng_state_1.pth +3 -0
- checkpoint-1500/rng_state_2.pth +3 -0
- checkpoint-1500/rng_state_3.pth +3 -0
- checkpoint-1500/rng_state_4.pth +3 -0
- checkpoint-1500/rng_state_5.pth +3 -0
- checkpoint-1500/rng_state_6.pth +3 -0
- checkpoint-1500/rng_state_7.pth +3 -0
- checkpoint-1500/scaler.pt +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +0 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/config.json +99 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/preprocessor_config.json +9 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state_0.pth +3 -0
- checkpoint-2000/rng_state_1.pth +3 -0
- checkpoint-2000/rng_state_2.pth +3 -0
- checkpoint-2000/rng_state_3.pth +3 -0
- checkpoint-2000/rng_state_4.pth +3 -0
- checkpoint-2000/rng_state_5.pth +3 -0
- checkpoint-2000/rng_state_6.pth +3 -0
- checkpoint-2000/rng_state_7.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +0 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/config.json +99 -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_0.pth +3 -0
- checkpoint-2500/rng_state_1.pth +3 -0
- checkpoint-2500/rng_state_2.pth +3 -0
- checkpoint-2500/rng_state_3.pth +3 -0
- checkpoint-2500/rng_state_4.pth +3 -0
- checkpoint-2500/rng_state_5.pth +3 -0
- checkpoint-2500/rng_state_6.pth +3 -0
- checkpoint-2500/rng_state_7.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +0 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 0.0829
|
19 |
+
- Wer: 0.0675
|
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: 4
|
40 |
+
- eval_batch_size: 4
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 8
|
44 |
+
- total_train_batch_size: 32
|
45 |
+
- total_eval_batch_size: 32
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 3.0
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
56 |
+
| 2.8805 | 0.34 | 300 | 2.8686 | 1.0 |
|
57 |
+
| 0.2459 | 0.67 | 600 | 0.1858 | 0.1554 |
|
58 |
+
| 0.1114 | 1.01 | 900 | 0.1379 | 0.1191 |
|
59 |
+
| 0.0867 | 1.35 | 1200 | 0.1130 | 0.0961 |
|
60 |
+
| 0.0698 | 1.68 | 1500 | 0.1032 | 0.0877 |
|
61 |
+
| 0.0663 | 2.02 | 1800 | 0.0959 | 0.0785 |
|
62 |
+
| 0.0451 | 2.35 | 2100 | 0.0887 | 0.0748 |
|
63 |
+
| 0.0392 | 2.69 | 2400 | 0.0859 | 0.0698 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.15.0.dev0
|
69 |
+
- Pytorch 1.9.0+cu111
|
70 |
+
- Datasets 1.16.2.dev0
|
71 |
+
- 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": 3.0,
|
3 |
+
"eval_loss": 0.08290250599384308,
|
4 |
+
"eval_runtime": 36.6763,
|
5 |
+
"eval_samples": 2642,
|
6 |
+
"eval_samples_per_second": 72.036,
|
7 |
+
"eval_steps_per_second": 2.263,
|
8 |
+
"eval_wer": 0.0675327251090837,
|
9 |
+
"train_loss": 0.5498764924440528,
|
10 |
+
"train_runtime": 2191.2667,
|
11 |
+
"train_samples": 28538,
|
12 |
+
"train_samples_per_second": 39.071,
|
13 |
+
"train_steps_per_second": 1.221
|
14 |
+
}
|
checkpoint-1500/config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": "4.15.0.dev0",
|
97 |
+
"use_weighted_layer_sum": false,
|
98 |
+
"vocab_size": 31
|
99 |
+
}
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c261e15539a8157be941fd7624dae5128dcbe95940dd1b840dd93ac297d43a77
|
3 |
+
size 721780605
|
checkpoint-1500/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-1500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:458c53801e858e3b930f21a29a9da4881e167461e35e4ab46c2806fd2959b509
|
3 |
+
size 377719629
|
checkpoint-1500/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5ed53ce1098cde69e2c41b154e80d4b067e5de796e58aa2c91d8028c7cc245f
|
3 |
+
size 14503
|
checkpoint-1500/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8f2073ec45692dcbfe8b7defb94fe3cd2c162e7a1344419238eac104b30e1c9
|
3 |
+
size 14503
|
checkpoint-1500/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d95fba3f31779ebfa1ee2c5fe0b6bb571092d62247af342494128c04d8b6dfa
|
3 |
+
size 14503
|
checkpoint-1500/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a72202df4409ba1c4d06e5f36f7d539893f23069901b3aa21f41a1453b03f77
|
3 |
+
size 14567
|
checkpoint-1500/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4233baed3955b4078f9ec822069ac30da0461eb4d6867d7984f178905c36aa5
|
3 |
+
size 14503
|
checkpoint-1500/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c355d10e0d422d7c3a02f6fec69db6f53570c05bfc18241f7c56ecbaeebbccdf
|
3 |
+
size 14503
|
checkpoint-1500/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ad262dbf8fcc7f2f4883e08d99c44225c9a21eae8149a02082486ae78870464
|
3 |
+
size 14567
|
checkpoint-1500/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:452de0ab02fc02363e64c61dab106e0abafbf6b118b4eb26827fa8d111a07a42
|
3 |
+
size 14503
|
checkpoint-1500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7fbc7a144029003722430516d1c5308f93f73415bdc7ecc658587580e84348b
|
3 |
+
size 559
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27ab9eb70cb6246d9fd2a2200ec4d73b9112190fc66c1a54d4a71fc847bd897
|
3 |
+
size 623
|
checkpoint-1500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8761478b99a12db075e5e6c132f753838ac53d73091dcdeaa58795d88d3db9c4
|
3 |
+
size 2991
|
checkpoint-2000/config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": "4.15.0.dev0",
|
97 |
+
"use_weighted_layer_sum": false,
|
98 |
+
"vocab_size": 31
|
99 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e950d2b66644899b794ea84c59c70203c151a6944d7ff5b53f912ea78e670408
|
3 |
+
size 721780605
|
checkpoint-2000/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-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3775a6aeeed32d4e92bd30f4ffaab87675463bad096eacfbf3c14c69dd9bf8bd
|
3 |
+
size 377719629
|
checkpoint-2000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5569d295f6b04e68dedd1d1e47af332abdd8dee7016de629767a89f0e376cf2f
|
3 |
+
size 14567
|
checkpoint-2000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be6d93a6f6c87b8ae653439c54185f21f32a1f5ec9b6c20b798960ffb8492201
|
3 |
+
size 14503
|
checkpoint-2000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a19cf0616bd338e31b18d6ddcb9405b28ae030a73040208acc88256c1efbe6d
|
3 |
+
size 14567
|
checkpoint-2000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7663ab231b5fc9c1550d7c93d520d5e4d2b969531da59bb6ce6c35cec6d17bf9
|
3 |
+
size 14503
|
checkpoint-2000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ecda2420c738c88acce616d7be3e8d6537a1c9d11458c1a75752d2e5fd5c999
|
3 |
+
size 14503
|
checkpoint-2000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efcc7ba06ac52d111aede50095580d57fd6d9e92799eda5ea996e1ef5fd316a5
|
3 |
+
size 14567
|
checkpoint-2000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36eadfc1697fbe65691efae500577b437e9e009c4b5f4c3818de79c1fae7d070
|
3 |
+
size 14503
|
checkpoint-2000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ede43c535465004dda19399c8874cee1a403cdc67dc99875ccba01bb3bdf258c
|
3 |
+
size 14567
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b413df0e3fdc26c93f450ad518eaa38cfe8b0cc100ff71800f9bb58f474075f7
|
3 |
+
size 559
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d46baafea37d93937203726a289698197cf00554392c50e1972bbe5dda0e2ecc
|
3 |
+
size 623
|
checkpoint-2000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8761478b99a12db075e5e6c132f753838ac53d73091dcdeaa58795d88d3db9c4
|
3 |
+
size 2991
|
checkpoint-2500/config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": "4.15.0.dev0",
|
97 |
+
"use_weighted_layer_sum": false,
|
98 |
+
"vocab_size": 31
|
99 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68d33b01ee02622dee733be4a53fba1da3266da83f3d3adbb1a3e73a31f0f6b3
|
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:a5061df97e4630f6a7504728a3325b2f89ca1d46a19a255de0c2c398544c82ea
|
3 |
+
size 377719629
|
checkpoint-2500/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d904d188766e6e035695822a4885cd4041bc536e6d9ffbc223d95d9ddfc33c2
|
3 |
+
size 14567
|
checkpoint-2500/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59d6fe5fb6acb6733912ed776eb8fe0bae77d9b5ab563bfcc36f005b2a217793
|
3 |
+
size 14503
|
checkpoint-2500/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:218592c68be449af1e31fe01c6bba53ecf97e2a4cd6452b80323202c42675afb
|
3 |
+
size 14503
|
checkpoint-2500/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b4164413f865076334826b1dd3ffadd9cb0955fb537f09f559944bb0329e96
|
3 |
+
size 14567
|
checkpoint-2500/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0f8503bd9ae573b2a8febae9af8accac94c892e0343f60f66b9c6ee492be0a4
|
3 |
+
size 14567
|
checkpoint-2500/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82796e1a4fecc1605ca85f74fe602f2ce129a2523d76fdeb73227d4e0600baf5
|
3 |
+
size 14567
|
checkpoint-2500/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde0e76604d32da9f9a5e181255f641a46bc4a1083e6d6ed30add6b07c3597cf
|
3 |
+
size 14503
|
checkpoint-2500/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c48d304ed20ff3ee7c680665b2483f89ce2d4cd273b24633b42d89d4b19da295
|
3 |
+
size 14567
|
checkpoint-2500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6fd7eec1b9d090dadb486adaa0119fe5d9ddcc4307d12300046d7a69f24d4fb
|
3 |
+
size 559
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:126808669fdd8ee0a9deb4a3d3de9daa11b50bc200d48bf34dcbb2e4fbca0770
|
3 |
+
size 623
|
checkpoint-2500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|