add tokenizer
Browse files- checkpoint-10000/config.json +86 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/preprocessor_config.json +9 -0
- checkpoint-10000/pytorch_model.bin +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scaler.pt +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/trainer_state.json +0 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-9250/config.json +86 -0
- checkpoint-9250/optimizer.pt +3 -0
- checkpoint-9250/preprocessor_config.json +9 -0
- checkpoint-9250/pytorch_model.bin +3 -0
- checkpoint-9250/rng_state.pth +3 -0
- checkpoint-9250/scaler.pt +3 -0
- checkpoint-9250/scheduler.pt +3 -0
- checkpoint-9250/trainer_state.json +0 -0
- checkpoint-9250/training_args.bin +3 -0
- checkpoint-9500/config.json +86 -0
- checkpoint-9500/optimizer.pt +3 -0
- checkpoint-9500/preprocessor_config.json +9 -0
- checkpoint-9500/pytorch_model.bin +3 -0
- checkpoint-9500/rng_state.pth +3 -0
- checkpoint-9500/scaler.pt +3 -0
- checkpoint-9500/scheduler.pt +3 -0
- checkpoint-9500/trainer_state.json +0 -0
- checkpoint-9500/training_args.bin +3 -0
- checkpoint-9750/config.json +86 -0
- checkpoint-9750/optimizer.pt +3 -0
- checkpoint-9750/preprocessor_config.json +9 -0
- checkpoint-9750/pytorch_model.bin +3 -0
- checkpoint-9750/rng_state.pth +3 -0
- checkpoint-9750/scaler.pt +3 -0
- checkpoint-9750/scheduler.pt +3 -0
- checkpoint-9750/trainer_state.json +0 -0
- checkpoint-9750/training_args.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
checkpoint-10000/config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.036,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.05,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.025,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"layerdrop": 0.02,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_min_space": 1,
|
61 |
+
"mask_channel_other": 0.0,
|
62 |
+
"mask_channel_prob": 0.0,
|
63 |
+
"mask_channel_selection": "static",
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_prob": 0.0,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_space": 1,
|
68 |
+
"mask_time_other": 0.0,
|
69 |
+
"mask_time_prob": 0.057,
|
70 |
+
"mask_time_selection": "static",
|
71 |
+
"model_type": "wav2vec2",
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"pad_token_id": 29,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.11.3",
|
84 |
+
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 30
|
86 |
+
}
|
checkpoint-10000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:895c3f48477f127a039a30459cde57839cdf56af3abfd9f633de7a0d481e41e9
|
3 |
+
size 2490304913
|
checkpoint-10000/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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-10000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1bd22dcb131b297e0ca6f74bc1edd3c68f79f280d70ffb071322f27942babd6
|
3 |
+
size 1262046641
|
checkpoint-10000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:411127d4a3138c8e77291c6c050bf7c67727b2f4cf309d227ce6efe8c860d397
|
3 |
+
size 14567
|
checkpoint-10000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dccb30368168f99edf97591b771e200a84ed533a1eccbd32ffc77fe05e23623
|
3 |
+
size 559
|
checkpoint-10000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3f89de626762336df67d4ac94716de7493232ca7ab1acae963a8bc705bf8d4
|
3 |
+
size 623
|
checkpoint-10000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3fcce7c9ce67f8c0e27e7ec968071b23cc69583cb57e70631995198c3ec2b6
|
3 |
+
size 2863
|
checkpoint-9250/config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.036,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.05,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.025,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"layerdrop": 0.02,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_min_space": 1,
|
61 |
+
"mask_channel_other": 0.0,
|
62 |
+
"mask_channel_prob": 0.0,
|
63 |
+
"mask_channel_selection": "static",
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_prob": 0.0,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_space": 1,
|
68 |
+
"mask_time_other": 0.0,
|
69 |
+
"mask_time_prob": 0.057,
|
70 |
+
"mask_time_selection": "static",
|
71 |
+
"model_type": "wav2vec2",
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"pad_token_id": 29,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.11.3",
|
84 |
+
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 30
|
86 |
+
}
|
checkpoint-9250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f95222c0b8853fcc4892df537c6d7c749ffd453842d8ff40956eadd253b156f
|
3 |
+
size 2490304913
|
checkpoint-9250/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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-9250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:118f1df4a94e0f6a402b5483712041f5c1c8086987fda7f46dc85856eae1ff09
|
3 |
+
size 1262046641
|
checkpoint-9250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4cda3345baae66a996a88b66f8016edd5b1bf87d24b298ab4264f67146c7cfd
|
3 |
+
size 14567
|
checkpoint-9250/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f4a23020b94c74dd47f9697d19d7f4e4215b0ef64bf238fe0fb36d9b7db8e35
|
3 |
+
size 559
|
checkpoint-9250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe6877a43299075202cc32f060a41bad769669f14e1e462e886ec500a305ba7c
|
3 |
+
size 623
|
checkpoint-9250/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-9250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3fcce7c9ce67f8c0e27e7ec968071b23cc69583cb57e70631995198c3ec2b6
|
3 |
+
size 2863
|
checkpoint-9500/config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.036,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.05,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.025,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"layerdrop": 0.02,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_min_space": 1,
|
61 |
+
"mask_channel_other": 0.0,
|
62 |
+
"mask_channel_prob": 0.0,
|
63 |
+
"mask_channel_selection": "static",
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_prob": 0.0,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_space": 1,
|
68 |
+
"mask_time_other": 0.0,
|
69 |
+
"mask_time_prob": 0.057,
|
70 |
+
"mask_time_selection": "static",
|
71 |
+
"model_type": "wav2vec2",
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"pad_token_id": 29,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.11.3",
|
84 |
+
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 30
|
86 |
+
}
|
checkpoint-9500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80599b50341c4703908dee1ac13980ee22388412d11fb357ec20181662dc49be
|
3 |
+
size 2490304913
|
checkpoint-9500/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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-9500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f1ff935b3429bab7c5ac4918cc3246e4b3a83bd74e26b564f1c5227b53425f4
|
3 |
+
size 1262046641
|
checkpoint-9500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6f613f16461085b7272cff916a7e65a0b661254469d0472b0ee691fb80e9916
|
3 |
+
size 14567
|
checkpoint-9500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d0766e2e0a2eb3c82cc20ba593095f5bbb963f68aa45578f85e2745878900d
|
3 |
+
size 559
|
checkpoint-9500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c46f2c6088f1c1989d74ddb51a876f2d101807b4559b0afc21969ec0f234d5e5
|
3 |
+
size 623
|
checkpoint-9500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-9500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3fcce7c9ce67f8c0e27e7ec968071b23cc69583cb57e70631995198c3ec2b6
|
3 |
+
size 2863
|
checkpoint-9750/config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.036,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.05,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.025,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"layerdrop": 0.02,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_min_space": 1,
|
61 |
+
"mask_channel_other": 0.0,
|
62 |
+
"mask_channel_prob": 0.0,
|
63 |
+
"mask_channel_selection": "static",
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_prob": 0.0,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_space": 1,
|
68 |
+
"mask_time_other": 0.0,
|
69 |
+
"mask_time_prob": 0.057,
|
70 |
+
"mask_time_selection": "static",
|
71 |
+
"model_type": "wav2vec2",
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_codevector_groups": 2,
|
74 |
+
"num_codevectors_per_group": 320,
|
75 |
+
"num_conv_pos_embedding_groups": 16,
|
76 |
+
"num_conv_pos_embeddings": 128,
|
77 |
+
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
+
"num_negatives": 100,
|
80 |
+
"pad_token_id": 29,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.11.3",
|
84 |
+
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 30
|
86 |
+
}
|
checkpoint-9750/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edb11bb9ee56583936710a809b3ca869d7bf2267d8831cd907b5f615658beb66
|
3 |
+
size 2490304913
|
checkpoint-9750/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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-9750/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b150ba15d114a1c955f7210df4d7e2dd67095eb1e9fd41e74dfcd7d6e3c0831
|
3 |
+
size 1262046641
|
checkpoint-9750/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:187c8328a8ab26ccbf0dc77142ce23c50d726588f660106e7d87e37042cb612f
|
3 |
+
size 14503
|
checkpoint-9750/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f076ec0fb1be16c49493a7be75fd388cd53d792eac13afe07b4cb9fd6e2d4de
|
3 |
+
size 559
|
checkpoint-9750/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:292bc62b529a1626ebf1298b559c1d205e544348101842b21afb4d8d2d90af99
|
3 |
+
size 623
|
checkpoint-9750/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-9750/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3fcce7c9ce67f8c0e27e7ec968071b23cc69583cb57e70631995198c3ec2b6
|
3 |
+
size 2863
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"w": 0, "d": 2, "y": 3, "z": 4, "x": 5, "s": 6, "e": 7, "p": 8, "v": 9, "g": 10, "l": 11, "o": 12, "'": 13, "t": 14, "c": 15, "f": 16, "q": 17, "r": 18, "b": 19, "n": 20, "j": 21, "a": 22, "h": 23, "k": 24, "u": 25, "i": 26, "m": 27, "|": 1, "[UNK]": 28, "[PAD]": 29}
|