init commit
Browse files- config.json +76 -0
- optimizer.pt +3 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- trainer_state.json +44 -0
- training_args.bin +3 -0
- vocab.json +1 -0
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"conv_bias": true,
|
11 |
+
"conv_dim": [
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512
|
19 |
+
],
|
20 |
+
"conv_kernel": [
|
21 |
+
10,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
2,
|
27 |
+
2
|
28 |
+
],
|
29 |
+
"conv_stride": [
|
30 |
+
5,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2
|
37 |
+
],
|
38 |
+
"ctc_loss_reduction": "mean",
|
39 |
+
"ctc_zero_infinity": false,
|
40 |
+
"do_stable_layer_norm": true,
|
41 |
+
"eos_token_id": 2,
|
42 |
+
"feat_extract_activation": "gelu",
|
43 |
+
"feat_extract_dropout": 0.0,
|
44 |
+
"feat_extract_norm": "layer",
|
45 |
+
"feat_proj_dropout": 0.0,
|
46 |
+
"final_dropout": 0.0,
|
47 |
+
"gradient_checkpointing": true,
|
48 |
+
"hidden_act": "gelu",
|
49 |
+
"hidden_dropout": 0.1,
|
50 |
+
"hidden_size": 1024,
|
51 |
+
"initializer_range": 0.02,
|
52 |
+
"intermediate_size": 4096,
|
53 |
+
"layer_norm_eps": 1e-05,
|
54 |
+
"layerdrop": 0.1,
|
55 |
+
"mask_channel_length": 10,
|
56 |
+
"mask_channel_min_space": 1,
|
57 |
+
"mask_channel_other": 0.0,
|
58 |
+
"mask_channel_prob": 0.0,
|
59 |
+
"mask_channel_selection": "static",
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 0.0,
|
62 |
+
"mask_time_length": 10,
|
63 |
+
"mask_time_min_space": 1,
|
64 |
+
"mask_time_other": 0.0,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"mask_time_selection": "static",
|
67 |
+
"model_type": "wav2vec2",
|
68 |
+
"num_attention_heads": 16,
|
69 |
+
"num_conv_pos_embedding_groups": 16,
|
70 |
+
"num_conv_pos_embeddings": 128,
|
71 |
+
"num_feat_extract_layers": 7,
|
72 |
+
"num_hidden_layers": 24,
|
73 |
+
"pad_token_id": 68,
|
74 |
+
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 69
|
76 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed0b9aab1b5d4939b3837d0eafb88c9414dc36d03b51d1b481213de99f65398
|
3 |
+
size 2490642951
|
preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": true,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:171ae3aec748b1859b2ff82bb47a582e758bf4c7f0aa11dbb61381e0250a29c9
|
3 |
+
size 1262216727
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d1d4d1d0e39a33d7bfef8bc1082ecd1abc1d0342f6a0c947ca5b38bb8689ee
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 21.05263157894737,
|
5 |
+
"global_step": 800,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 10.53,
|
12 |
+
"learning_rate": 0.00023999999999999998,
|
13 |
+
"loss": 6.4582,
|
14 |
+
"step": 400
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 10.53,
|
18 |
+
"eval_loss": 2.820686101913452,
|
19 |
+
"eval_runtime": 541.4545,
|
20 |
+
"eval_samples_per_second": 4.041,
|
21 |
+
"eval_wer": 0.9957617789520036,
|
22 |
+
"step": 400
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 21.05,
|
26 |
+
"learning_rate": 0.00015937499999999998,
|
27 |
+
"loss": 0.692,
|
28 |
+
"step": 800
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 21.05,
|
32 |
+
"eval_loss": 0.5226749777793884,
|
33 |
+
"eval_runtime": 547.3066,
|
34 |
+
"eval_samples_per_second": 3.998,
|
35 |
+
"eval_wer": 0.41655658300308235,
|
36 |
+
"step": 800
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"max_steps": 1140,
|
40 |
+
"num_train_epochs": 30,
|
41 |
+
"total_flos": 1.379922511881828e+19,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81db272250312b3f79b8a3f96540f086f35cd461b6951c4799c0ffa6bf4e07eb
|
3 |
+
size 2287
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"\u0e37": 0, "\u0e0b": 1, "\u0e06": 2, "\u0e0d": 3, "\u0e07": 4, "\u0e02": 5, "\u0e49": 6, "\u0e2c": 7, "\u0e22": 8, "\u0e16": 9, "\u0e2e": 10, "\u0e2b": 11, "\u0e1b": 12, "\u0e4c": 13, "\u0e35": 14, "\u0e1f": 15, "\u0e1d": 16, "\u0e47": 17, "\u0e2d": 18, "\u0e08": 19, "\u0e0a": 20, "\u0e28": 21, "\u0e34": 22, "\u0e25": 23, "\u0e32": 24, "\u0e1a": 25, "\u0e40": 26, "\u0e29": 27, "\u0e38": 28, "\u0e39": 30, "\u0e36": 31, "\u0e1e": 32, "\u0e04": 33, "\u0e09": 34, "\u0e12": 35, "\u0e15": 36, "\u0e0e": 37, "\u0e10": 38, "\u0e4b": 39, "\u0e46": 40, "\u0e45": 41, "\u0e17": 42, "\u0e41": 43, "\u0e30": 44, "\u0e44": 45, "\u0e01": 46, "\u0e14": 47, "\u0e24": 48, "\u0e31": 49, "\u0e0f": 50, "\u0e20": 51, "\u0e19": 52, "\u0e2a": 53, "\u0e4d": 54, "\u0e43": 55, "\u0e27": 56, "\u0e42": 57, "\u0e33": 58, "\u0e18": 59, "\u0e48": 60, "\u0e21": 61, "\u0e13": 62, "\u0e1c": 63, "\u0e4a": 64, "\u0e11": 65, "\u0e23": 66, "|": 29, "[UNK]": 67, "[PAD]": 68}
|