Upload 9 files
Browse files- all_results.json +15 -0
- eval_results.json +9 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +15 -0
- train_results.json +9 -0
- trainer_state.json +58 -0
- training_args.bin +3 -0
- vocab.json +42 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.51,
|
3 |
+
"eval_loss": 3.0585784912109375,
|
4 |
+
"eval_runtime": 16.4746,
|
5 |
+
"eval_samples": 200,
|
6 |
+
"eval_samples_per_second": 12.14,
|
7 |
+
"eval_steps_per_second": 3.035,
|
8 |
+
"eval_wer": 0.4547531992687386,
|
9 |
+
"total_flos": 1.746851843427936e+16,
|
10 |
+
"train_loss": 2.2491682052612303,
|
11 |
+
"train_runtime": 96.9606,
|
12 |
+
"train_samples": 154,
|
13 |
+
"train_samples_per_second": 0.794,
|
14 |
+
"train_steps_per_second": 0.206
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.51,
|
3 |
+
"eval_loss": 3.0585784912109375,
|
4 |
+
"eval_runtime": 16.4746,
|
5 |
+
"eval_samples": 200,
|
6 |
+
"eval_samples_per_second": 12.14,
|
7 |
+
"eval_steps_per_second": 3.035,
|
8 |
+
"eval_wer": 0.4547531992687386
|
9 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"processor_class": "Wav2Vec2Processor",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"target_lang": null,
|
11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
12 |
+
"tokenizer_file": null,
|
13 |
+
"unk_token": "<unk>",
|
14 |
+
"word_delimiter_token": "|"
|
15 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.51,
|
3 |
+
"total_flos": 1.746851843427936e+16,
|
4 |
+
"train_loss": 2.2491682052612303,
|
5 |
+
"train_runtime": 96.9606,
|
6 |
+
"train_samples": 154,
|
7 |
+
"train_samples_per_second": 0.794,
|
8 |
+
"train_steps_per_second": 0.206
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5128205128205128,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 20,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.26,
|
13 |
+
"learning_rate": 1.8e-06,
|
14 |
+
"loss": 2.4415,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.26,
|
19 |
+
"eval_loss": 3.103879928588867,
|
20 |
+
"eval_runtime": 16.1503,
|
21 |
+
"eval_samples_per_second": 12.384,
|
22 |
+
"eval_steps_per_second": 3.096,
|
23 |
+
"eval_wer": 0.4556672760511883,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.51,
|
28 |
+
"learning_rate": 3.8e-06,
|
29 |
+
"loss": 2.0569,
|
30 |
+
"step": 20
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.51,
|
34 |
+
"eval_loss": 3.0585784912109375,
|
35 |
+
"eval_runtime": 15.679,
|
36 |
+
"eval_samples_per_second": 12.756,
|
37 |
+
"eval_steps_per_second": 3.189,
|
38 |
+
"eval_wer": 0.4547531992687386,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.51,
|
43 |
+
"step": 20,
|
44 |
+
"total_flos": 1.746851843427936e+16,
|
45 |
+
"train_loss": 2.2491682052612303,
|
46 |
+
"train_runtime": 96.9606,
|
47 |
+
"train_samples_per_second": 0.794,
|
48 |
+
"train_steps_per_second": 0.206
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 10,
|
52 |
+
"max_steps": 20,
|
53 |
+
"num_train_epochs": 1,
|
54 |
+
"save_steps": 10,
|
55 |
+
"total_flos": 1.746851843427936e+16,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c107e295d8cbc38ab79f97ca32294ef152583c1e0713b6994d965eab56ae1790
|
3 |
+
size 4091
|
vocab.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<pad>": 0,
|
4 |
+
"<s>": 1,
|
5 |
+
"<unk>": 3,
|
6 |
+
"|": 4,
|
7 |
+
"آ": 5,
|
8 |
+
"ئ": 6,
|
9 |
+
"ا": 7,
|
10 |
+
"ب": 8,
|
11 |
+
"ت": 9,
|
12 |
+
"ث": 10,
|
13 |
+
"ج": 11,
|
14 |
+
"ح": 12,
|
15 |
+
"خ": 13,
|
16 |
+
"د": 14,
|
17 |
+
"ذ": 15,
|
18 |
+
"ر": 16,
|
19 |
+
"ز": 17,
|
20 |
+
"س": 18,
|
21 |
+
"ش": 19,
|
22 |
+
"ص": 20,
|
23 |
+
"ض": 21,
|
24 |
+
"ط": 22,
|
25 |
+
"ظ": 23,
|
26 |
+
"ع": 24,
|
27 |
+
"غ": 25,
|
28 |
+
"ف": 26,
|
29 |
+
"ق": 27,
|
30 |
+
"ل": 28,
|
31 |
+
"م": 29,
|
32 |
+
"ن": 30,
|
33 |
+
"ه": 31,
|
34 |
+
"و": 32,
|
35 |
+
"پ": 33,
|
36 |
+
"چ": 34,
|
37 |
+
"ژ": 35,
|
38 |
+
"ک": 36,
|
39 |
+
"گ": 37,
|
40 |
+
"ی": 38,
|
41 |
+
"": 39
|
42 |
+
}
|