marinone94
commited on
Commit
Β·
53cd7e6
1
Parent(s):
f0c6c20
Training in progress, step 1000
Browse files- .ipynb_checkpoints/run-checkpoint.sh +12 -9
- {checkpoint-480 β checkpoint-1000}/config.json +0 -0
- {checkpoint-480 β checkpoint-1000}/optimizer.pt +1 -1
- {checkpoint-480 β checkpoint-1000}/preprocessor_config.json +0 -0
- {checkpoint-480 β checkpoint-1000}/pytorch_model.bin +1 -1
- checkpoint-1000/rng_state.pth +3 -0
- {checkpoint-480 β checkpoint-1000}/scaler.pt +1 -1
- {checkpoint-480 β checkpoint-1000}/scheduler.pt +1 -1
- checkpoint-1000/trainer_state.json +85 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-768/config.json +115 -0
- checkpoint-768/optimizer.pt +3 -0
- checkpoint-768/preprocessor_config.json +9 -0
- checkpoint-768/pytorch_model.bin +3 -0
- {checkpoint-480 β checkpoint-768}/rng_state.pth +1 -1
- checkpoint-768/scaler.pt +3 -0
- checkpoint-768/scheduler.pt +3 -0
- {checkpoint-480 β checkpoint-768}/trainer_state.json +48 -3
- {checkpoint-480 β checkpoint-768}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
- run.sh +3 -3
- special_tokens_map.json +1 -1
- training_args.bin +1 -1
.ipynb_checkpoints/run-checkpoint.sh
CHANGED
@@ -1,25 +1,28 @@
|
|
1 |
python run_speech_recognition_ctc.py \
|
2 |
-
--dataset_name="mozilla-foundation/
|
3 |
--model_name_or_path="KBLab/wav2vec2-large-voxrex" \
|
4 |
--dataset_config_name="sv-SE" \
|
|
|
|
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
-
--num_train_epochs="
|
8 |
-
--per_device_train_batch_size="
|
9 |
-
--per_device_eval_batch_size="
|
10 |
--gradient_accumulation_steps="4" \
|
11 |
--learning_rate="7.5e-5" \
|
12 |
-
--
|
13 |
--length_column_name="input_length" \
|
14 |
--evaluation_strategy="steps" \
|
|
|
|
|
|
|
15 |
--text_column_name="sentence" \
|
16 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
17 |
-
--save_steps="500" \
|
18 |
-
--eval_steps="500" \
|
19 |
--logging_steps="100" \
|
20 |
--layerdrop="0.0" \
|
21 |
-
--activation_dropout="0.
|
22 |
-
--save_total_limit="
|
23 |
--freeze_feature_encoder \
|
24 |
--feat_proj_dropout="0.0" \
|
25 |
--mask_time_prob="0.75" \
|
|
|
1 |
python run_speech_recognition_ctc.py \
|
2 |
+
--dataset_name="mozilla-foundation/common_voice_9_0" \
|
3 |
--model_name_or_path="KBLab/wav2vec2-large-voxrex" \
|
4 |
--dataset_config_name="sv-SE" \
|
5 |
+
--train_split_name="train+validation" \
|
6 |
+
--eval_split_name="test" \
|
7 |
--output_dir="./" \
|
8 |
--overwrite_output_dir \
|
9 |
+
--num_train_epochs="100" \
|
10 |
+
--per_device_train_batch_size="32" \
|
11 |
+
--per_device_eval_batch_size="32" \
|
12 |
--gradient_accumulation_steps="4" \
|
13 |
--learning_rate="7.5e-5" \
|
14 |
+
--warmup_ratio="0.2" \
|
15 |
--length_column_name="input_length" \
|
16 |
--evaluation_strategy="steps" \
|
17 |
+
--save_strategy="steps" \
|
18 |
+
--eval_steps="1000" \
|
19 |
+
--save_steps="1000" \
|
20 |
--text_column_name="sentence" \
|
21 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
|
|
|
|
22 |
--logging_steps="100" \
|
23 |
--layerdrop="0.0" \
|
24 |
+
--activation_dropout="0.15" \
|
25 |
+
--save_total_limit="2" \
|
26 |
--freeze_feature_encoder \
|
27 |
--feat_proj_dropout="0.0" \
|
28 |
--mask_time_prob="0.75" \
|
{checkpoint-480 β checkpoint-1000}/config.json
RENAMED
File without changes
|
{checkpoint-480 β checkpoint-1000}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e19d42b0d868c0027f986e2375d72fdfef0c3b4418f306ca68f3229412a925bb
|
3 |
size 2490337809
|
{checkpoint-480 β checkpoint-1000}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-480 β checkpoint-1000}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9ea0cc96b8e5bbae5dd33b444779900e8411a85ceceeeb644e8b71cf1d6010
|
3 |
size 1262063089
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7093ed8441dc6153f9584135490f60eae09d1eb18db49dacd1b3df44ea1fba00
|
3 |
+
size 14631
|
{checkpoint-480 β checkpoint-1000}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da34b372f0657769030e38eac6fb8c8be38a78601419da4133972b101bc446c3
|
3 |
size 559
|
{checkpoint-480 β checkpoint-1000}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a17a6abbede83978b64af0551f8dd0bf1bc0f14488aed13a030be18065df696d
|
3 |
size 623
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.415584415584416,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.04,
|
12 |
+
"learning_rate": 3.828125e-06,
|
13 |
+
"loss": 15.104,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.08,
|
18 |
+
"learning_rate": 7.6953125e-06,
|
19 |
+
"loss": 12.2149,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.12,
|
24 |
+
"learning_rate": 1.16015625e-05,
|
25 |
+
"loss": 4.9885,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 4.17,
|
30 |
+
"learning_rate": 1.55078125e-05,
|
31 |
+
"loss": 3.3788,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 5.21,
|
36 |
+
"learning_rate": 1.94140625e-05,
|
37 |
+
"loss": 3.1705,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 6.25,
|
42 |
+
"learning_rate": 2.3320312499999995e-05,
|
43 |
+
"loss": 3.11,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 7.29,
|
48 |
+
"learning_rate": 2.72265625e-05,
|
49 |
+
"loss": 3.0526,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 8.33,
|
54 |
+
"learning_rate": 3.11328125e-05,
|
55 |
+
"loss": 3.0113,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 9.37,
|
60 |
+
"learning_rate": 3.5039062499999995e-05,
|
61 |
+
"loss": 2.9601,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 10.42,
|
66 |
+
"learning_rate": 3.89453125e-05,
|
67 |
+
"loss": 2.9099,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 10.42,
|
72 |
+
"eval_loss": 2.8369038105010986,
|
73 |
+
"eval_runtime": 198.5866,
|
74 |
+
"eval_samples_per_second": 25.405,
|
75 |
+
"eval_steps_per_second": 0.796,
|
76 |
+
"eval_wer": 1.0,
|
77 |
+
"step": 1000
|
78 |
+
}
|
79 |
+
],
|
80 |
+
"max_steps": 9600,
|
81 |
+
"num_train_epochs": 100,
|
82 |
+
"total_flos": 1.5571160176119996e+19,
|
83 |
+
"trial_name": null,
|
84 |
+
"trial_params": null
|
85 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f8dab6838e0cc8a253bbc1fb16c34a7a36619cf3b9e2bd9c1e4027635a3b2b
|
3 |
+
size 3055
|
checkpoint-768/config.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KBLab/wav2vec2-large-voxrex",
|
3 |
+
"activation_dropout": 0.15,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
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": true,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 1024,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 4096,
|
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": 64,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.25,
|
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": 0.75,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"model_type": "wav2vec2",
|
77 |
+
"num_adapter_layers": 3,
|
78 |
+
"num_attention_heads": 16,
|
79 |
+
"num_codevector_groups": 2,
|
80 |
+
"num_codevectors_per_group": 320,
|
81 |
+
"num_conv_pos_embedding_groups": 16,
|
82 |
+
"num_conv_pos_embeddings": 128,
|
83 |
+
"num_feat_extract_layers": 7,
|
84 |
+
"num_hidden_layers": 24,
|
85 |
+
"num_negatives": 100,
|
86 |
+
"output_hidden_size": 1024,
|
87 |
+
"pad_token_id": 31,
|
88 |
+
"proj_codevector_dim": 768,
|
89 |
+
"tdnn_dilation": [
|
90 |
+
1,
|
91 |
+
2,
|
92 |
+
3,
|
93 |
+
1,
|
94 |
+
1
|
95 |
+
],
|
96 |
+
"tdnn_dim": [
|
97 |
+
512,
|
98 |
+
512,
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
1500
|
102 |
+
],
|
103 |
+
"tdnn_kernel": [
|
104 |
+
5,
|
105 |
+
3,
|
106 |
+
3,
|
107 |
+
1,
|
108 |
+
1
|
109 |
+
],
|
110 |
+
"torch_dtype": "float32",
|
111 |
+
"transformers_version": "4.17.0.dev0",
|
112 |
+
"use_weighted_layer_sum": false,
|
113 |
+
"vocab_size": 34,
|
114 |
+
"xvector_output_dim": 512
|
115 |
+
}
|
checkpoint-768/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a9586ea872b7dc0314b8a87818664af900cbda0ab386e4009727f6c0d7b253a
|
3 |
+
size 2490337809
|
checkpoint-768/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,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
checkpoint-768/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc646c1fab9250df454893bcc01f9e038c38d131e6ae361e5b583738752166e
|
3 |
+
size 1262063089
|
{checkpoint-480 β checkpoint-768}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05cc372da27e61a6d138f62cea130dc4e1b6134306f029654ad0c9407d998ef2
|
3 |
size 14567
|
checkpoint-768/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2832d98d4b5feff45ebd720deebf0b82dd661e5c21aebec8b84b7733057fa4e5
|
3 |
+
size 559
|
checkpoint-768/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9748e33e2a1f1ebee6bb9c1ab72b7b9d1500e1f1c49e6b8e19aa252c6f8c658
|
3 |
+
size 623
|
{checkpoint-480 β checkpoint-768}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -75,11 +75,56 @@
|
|
75 |
"eval_steps_per_second": 0.849,
|
76 |
"eval_wer": 1.0,
|
77 |
"step": 480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
}
|
79 |
],
|
80 |
"max_steps": 19200,
|
81 |
"num_train_epochs": 200,
|
82 |
-
"total_flos":
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.997402597402598,
|
5 |
+
"global_step": 768,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
75 |
"eval_steps_per_second": 0.849,
|
76 |
"eval_wer": 1.0,
|
77 |
"step": 480
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 5.21,
|
81 |
+
"learning_rate": 7.765624999999999e-06,
|
82 |
+
"loss": 3.8196,
|
83 |
+
"step": 500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"eval_loss": 3.3380837440490723,
|
88 |
+
"eval_runtime": 183.9322,
|
89 |
+
"eval_samples_per_second": 27.429,
|
90 |
+
"eval_steps_per_second": 0.859,
|
91 |
+
"eval_wer": 1.0,
|
92 |
+
"step": 576
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.25,
|
96 |
+
"learning_rate": 9.328125e-06,
|
97 |
+
"loss": 3.3535,
|
98 |
+
"step": 600
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 3.2117931842803955,
|
103 |
+
"eval_runtime": 186.1,
|
104 |
+
"eval_samples_per_second": 27.109,
|
105 |
+
"eval_steps_per_second": 0.849,
|
106 |
+
"eval_wer": 1.0,
|
107 |
+
"step": 672
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 7.29,
|
111 |
+
"learning_rate": 1.0890624999999999e-05,
|
112 |
+
"loss": 3.1949,
|
113 |
+
"step": 700
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"eval_loss": 3.158613920211792,
|
118 |
+
"eval_runtime": 182.4287,
|
119 |
+
"eval_samples_per_second": 27.655,
|
120 |
+
"eval_steps_per_second": 0.866,
|
121 |
+
"eval_wer": 1.0,
|
122 |
+
"step": 768
|
123 |
}
|
124 |
],
|
125 |
"max_steps": 19200,
|
126 |
"num_train_epochs": 200,
|
127 |
+
"total_flos": 1.1926542720934052e+19,
|
128 |
"trial_name": null,
|
129 |
"trial_params": null
|
130 |
}
|
{checkpoint-480 β checkpoint-768}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9ea0cc96b8e5bbae5dd33b444779900e8411a85ceceeeb644e8b71cf1d6010
|
3 |
size 1262063089
|
run.sh
CHANGED
@@ -6,7 +6,7 @@ python run_speech_recognition_ctc.py \
|
|
6 |
--eval_split_name="test" \
|
7 |
--output_dir="./" \
|
8 |
--overwrite_output_dir \
|
9 |
-
--num_train_epochs="
|
10 |
--per_device_train_batch_size="32" \
|
11 |
--per_device_eval_batch_size="32" \
|
12 |
--gradient_accumulation_steps="4" \
|
@@ -15,8 +15,8 @@ python run_speech_recognition_ctc.py \
|
|
15 |
--length_column_name="input_length" \
|
16 |
--evaluation_strategy="steps" \
|
17 |
--save_strategy="steps" \
|
18 |
-
--eval_steps="
|
19 |
-
--save_steps="
|
20 |
--text_column_name="sentence" \
|
21 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
22 |
--logging_steps="100" \
|
|
|
6 |
--eval_split_name="test" \
|
7 |
--output_dir="./" \
|
8 |
--overwrite_output_dir \
|
9 |
+
--num_train_epochs="100" \
|
10 |
--per_device_train_batch_size="32" \
|
11 |
--per_device_eval_batch_size="32" \
|
12 |
--gradient_accumulation_steps="4" \
|
|
|
15 |
--length_column_name="input_length" \
|
16 |
--evaluation_strategy="steps" \
|
17 |
--save_strategy="steps" \
|
18 |
+
--eval_steps="1000" \
|
19 |
+
--save_steps="1000" \
|
20 |
--text_column_name="sentence" \
|
21 |
--chars_to_ignore , ? . ! \- \; \: \" β % β β οΏ½ β β β¦ β \
|
22 |
--logging_steps="100" \
|
special_tokens_map.json
CHANGED
@@ -1 +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}, {"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}, {"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}, {"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}, {"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}, {"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}]}
|
|
|
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}, {"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}, {"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}, {"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}, {"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}, {"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}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f8dab6838e0cc8a253bbc1fb16c34a7a36619cf3b9e2bd9c1e4027635a3b2b
|
3 |
size 3055
|