End of training
Browse files- README.md +118 -0
- config.json +275 -0
- generation_config.json +15 -0
- model.safetensors +3 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.47.csv +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.47_hyp.trn +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.47_ref.trn +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- common_voice_13_0
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: DeCRED_small_cv_2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# DeCRED_small_cv_2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_13_0 dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0669
|
21 |
+
- Cer: 0.0663
|
22 |
+
- Wer: 0.1563
|
23 |
+
- Mer: 0.1532
|
24 |
+
- Wil: 0.2546
|
25 |
+
- Wip: 0.7454
|
26 |
+
- Hits: 128002
|
27 |
+
- Substitutions: 17367
|
28 |
+
- Deletions: 2812
|
29 |
+
- Insertions: 2975
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 0.002
|
49 |
+
- train_batch_size: 128
|
50 |
+
- eval_batch_size: 64
|
51 |
+
- seed: 42
|
52 |
+
- distributed_type: multi-GPU
|
53 |
+
- num_devices: 2
|
54 |
+
- total_train_batch_size: 256
|
55 |
+
- total_eval_batch_size: 128
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- lr_scheduler_warmup_steps: 10000
|
59 |
+
- num_epochs: 50.0
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Cer | Deletions | Hits | Insertions | Validation Loss | Mer | Substitutions | Wer | Wil | Wip |
|
64 |
+
|:-------------:|:-----:|:------:|:------:|:---------:|:------:|:----------:|:---------------:|:------:|:-------------:|:------:|:------:|:------:|
|
65 |
+
| 1.6144 | 5.0 | 14885 | 0.1526 | 5701 | 107636 | 6856 | 1.4427 | 0.3057 | 34844 | 0.3199 | 0.4765 | 0.5235 |
|
66 |
+
| 1.5552 | 6.0 | 17862 | 0.1438 | 5401 | 109845 | 6588 | 1.3968 | 0.2903 | 32935 | 0.3032 | 0.4549 | 0.5451 |
|
67 |
+
| 1.5102 | 7.0 | 20839 | 0.1327 | 5227 | 112073 | 5890 | 1.3578 | 0.2726 | 30881 | 0.2834 | 0.4305 | 0.5695 |
|
68 |
+
| 1.4504 | 8.0 | 23816 | 0.1256 | 4512 | 113841 | 5758 | 1.3262 | 0.2605 | 29828 | 0.2706 | 0.4147 | 0.5853 |
|
69 |
+
| 1.4098 | 9.0 | 26793 | 0.1195 | 4580 | 115426 | 5441 | 1.2918 | 0.2486 | 28175 | 0.2578 | 0.3967 | 0.6033 |
|
70 |
+
| 1.3717 | 10.0 | 29770 | 0.1146 | 4666 | 116052 | 4869 | 1.2777 | 0.2417 | 27463 | 0.2497 | 0.3875 | 0.6125 |
|
71 |
+
| 1.3573 | 11.0 | 32747 | 0.1123 | 4193 | 117058 | 5268 | 1.2628 | 0.2372 | 26930 | 0.2456 | 0.3804 | 0.6196 |
|
72 |
+
| 1.3433 | 12.0 | 35724 | 0.1085 | 4814 | 117567 | 4293 | 1.2455 | 0.2289 | 25800 | 0.2356 | 0.3683 | 0.6317 |
|
73 |
+
| 1.3281 | 13.0 | 38701 | 0.1068 | 3789 | 118972 | 5402 | 1.2333 | 0.2254 | 25420 | 0.2336 | 0.3623 | 0.6377 |
|
74 |
+
| 1.3068 | 14.0 | 41678 | 0.1019 | 4076 | 119434 | 4622 | 1.2159 | 0.2184 | 24671 | 0.2252 | 0.3527 | 0.6473 |
|
75 |
+
| 1.2847 | 15.0 | 44655 | 0.1017 | 4042 | 119608 | 4683 | 1.2081 | 0.2176 | 24531 | 0.2244 | 0.3513 | 0.6487 |
|
76 |
+
| 1.2753 | 16.0 | 47632 | 0.1007 | 4211 | 119928 | 4304 | 1.2023 | 0.2135 | 24042 | 0.2197 | 0.3454 | 0.6546 |
|
77 |
+
| 1.2793 | 17.0 | 50609 | 0.0950 | 3660 | 121093 | 4365 | 1.1862 | 0.2062 | 23428 | 0.2123 | 0.3354 | 0.6646 |
|
78 |
+
| 1.2676 | 18.0 | 53586 | 0.0927 | 3813 | 121198 | 4207 | 1.1843 | 0.2047 | 23170 | 0.2105 | 0.3328 | 0.6672 |
|
79 |
+
| 1.2256 | 19.0 | 56563 | 0.0936 | 3948 | 121257 | 4033 | 1.1795 | 0.2034 | 22976 | 0.2089 | 0.3308 | 0.6692 |
|
80 |
+
| 1.2238 | 20.0 | 59540 | 0.0932 | 3634 | 121864 | 4372 | 1.1736 | 0.2012 | 22683 | 0.2071 | 0.3270 | 0.6730 |
|
81 |
+
| 1.2206 | 21.0 | 62517 | 0.0892 | 3862 | 122333 | 3732 | 1.1623 | 0.1947 | 21986 | 0.1996 | 0.3178 | 0.6822 |
|
82 |
+
| 1.2018 | 22.0 | 65494 | 0.0893 | 4037 | 122051 | 3703 | 1.1614 | 0.1964 | 22093 | 0.2013 | 0.3200 | 0.6800 |
|
83 |
+
| 1.1791 | 23.0 | 68471 | 1.1510 | 0.0868 | 0.1953 | 0.1906 | 0.3114 | 0.6886 | 122943 | 21479 | 3759 | 3708 |
|
84 |
+
| 1.1958 | 24.0 | 71448 | 1.1438 | 0.0855 | 0.1931 | 0.1883 | 0.3078 | 0.6922 | 123356 | 21215 | 3610 | 3784 |
|
85 |
+
| 1.1672 | 25.0 | 74425 | 1.1420 | 0.0863 | 0.1940 | 0.1891 | 0.3088 | 0.6912 | 123289 | 21266 | 3626 | 3861 |
|
86 |
+
| 1.1595 | 26.0 | 77402 | 1.1358 | 0.0843 | 0.1898 | 0.1852 | 0.3026 | 0.6974 | 123784 | 20743 | 3654 | 3735 |
|
87 |
+
| 1.1803 | 27.0 | 80379 | 1.1343 | 0.0838 | 0.1901 | 0.1856 | 0.3041 | 0.6959 | 123595 | 20966 | 3620 | 3580 |
|
88 |
+
| 1.1488 | 28.0 | 83356 | 1.1262 | 0.0810 | 0.1855 | 0.1809 | 0.2972 | 0.7028 | 124441 | 20511 | 3229 | 3746 |
|
89 |
+
| 1.1303 | 29.0 | 86333 | 1.1233 | 0.0801 | 0.1837 | 0.1793 | 0.2946 | 0.7054 | 124600 | 20302 | 3279 | 3636 |
|
90 |
+
| 1.1266 | 30.0 | 89310 | 1.1203 | 0.0791 | 0.1818 | 0.1777 | 0.2918 | 0.7082 | 124687 | 20007 | 3487 | 3447 |
|
91 |
+
| 1.14 | 31.0 | 92287 | 1.1179 | 0.0790 | 0.1813 | 0.1769 | 0.2905 | 0.7095 | 124938 | 19925 | 3318 | 3616 |
|
92 |
+
| 1.1151 | 32.0 | 95264 | 1.1115 | 0.0776 | 0.1794 | 0.1752 | 0.2885 | 0.7115 | 125137 | 19847 | 3197 | 3534 |
|
93 |
+
| 1.1043 | 33.0 | 98241 | 1.1080 | 0.0773 | 0.1785 | 0.1744 | 0.2866 | 0.7134 | 125253 | 19624 | 3304 | 3522 |
|
94 |
+
| 1.1157 | 34.0 | 101218 | 1.1039 | 0.0762 | 0.1750 | 0.1710 | 0.2817 | 0.7183 | 125705 | 19302 | 3174 | 3458 |
|
95 |
+
| 1.0911 | 35.0 | 104195 | 1.1004 | 0.0747 | 0.1740 | 0.1700 | 0.2800 | 0.7200 | 125869 | 19160 | 3152 | 3466 |
|
96 |
+
| 1.0722 | 36.0 | 107172 | 1.0978 | 0.0743 | 0.1719 | 0.1684 | 0.2776 | 0.7224 | 125819 | 18952 | 3410 | 3111 |
|
97 |
+
| 1.092 | 37.0 | 110149 | 1.0953 | 0.0742 | 0.1714 | 0.1676 | 0.2763 | 0.7237 | 126142 | 18878 | 3161 | 3362 |
|
98 |
+
| 1.0763 | 38.0 | 113126 | 1.0914 | 0.0722 | 0.1686 | 0.1651 | 0.2726 | 0.7274 | 126377 | 18617 | 3187 | 3181 |
|
99 |
+
| 1.0667 | 39.0 | 116103 | 1.0918 | 0.0729 | 0.1690 | 0.1654 | 0.2728 | 0.7272 | 126366 | 18602 | 3213 | 3224 |
|
100 |
+
| 1.0651 | 40.0 | 119080 | 1.0845 | 0.0718 | 0.1662 | 0.1627 | 0.2690 | 0.7310 | 126749 | 18373 | 3059 | 3191 |
|
101 |
+
| 1.0761 | 41.0 | 122057 | 1.0836 | 0.0703 | 0.1648 | 0.1614 | 0.2673 | 0.7327 | 126911 | 18271 | 2999 | 3156 |
|
102 |
+
| 1.0509 | 42.0 | 125034 | 1.0828 | 0.0709 | 0.1647 | 0.1615 | 0.2670 | 0.7330 | 126714 | 18177 | 3290 | 2942 |
|
103 |
+
| 1.0409 | 43.0 | 128011 | 1.0798 | 0.0707 | 0.1640 | 0.1607 | 0.2658 | 0.7342 | 126946 | 18103 | 3132 | 3070 |
|
104 |
+
| 1.0525 | 44.0 | 130988 | 1.0760 | 0.0688 | 0.1608 | 0.1575 | 0.2614 | 0.7386 | 127451 | 17870 | 2860 | 3100 |
|
105 |
+
| 1.0359 | 45.0 | 133965 | 1.0745 | 0.0680 | 0.1601 | 0.1568 | 0.2602 | 0.7398 | 127571 | 17771 | 2839 | 3115 |
|
106 |
+
| 1.0144 | 46.0 | 136942 | 1.0738 | 0.0681 | 0.1607 | 0.1574 | 0.2614 | 0.7386 | 127503 | 17888 | 2790 | 3139 |
|
107 |
+
| 1.054 | 47.0 | 139919 | 1.0691 | 0.0672 | 0.1586 | 0.1554 | 0.2578 | 0.7422 | 127745 | 17575 | 2861 | 3062 |
|
108 |
+
| 1.0427 | 48.0 | 142896 | 1.0681 | 0.0667 | 0.1573 | 0.1542 | 0.2562 | 0.7438 | 127851 | 17473 | 2857 | 2981 |
|
109 |
+
| 1.0067 | 49.0 | 145873 | 1.0682 | 0.0668 | 0.1568 | 0.1537 | 0.2553 | 0.7447 | 127906 | 17401 | 2874 | 2957 |
|
110 |
+
| 1.0054 | 50.0 | 148850 | 1.0669 | 0.0663 | 0.1563 | 0.1532 | 0.2546 | 0.7454 | 128002 | 17367 | 2812 | 2975 |
|
111 |
+
|
112 |
+
|
113 |
+
### Framework versions
|
114 |
+
|
115 |
+
- Transformers 4.40.0.dev0
|
116 |
+
- Pytorch 2.2.0+rocm5.6
|
117 |
+
- Datasets 2.18.0
|
118 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,275 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"JointCTCAttentionEncoderDecoder"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"ctc_weight": 0.3,
|
7 |
+
"decoder": {
|
8 |
+
"_name_or_path": "Lakoc/gpt2_256h_6l_add_head3_04",
|
9 |
+
"activation_function": "gelu_new",
|
10 |
+
"add_cross_attention": true,
|
11 |
+
"architectures": null,
|
12 |
+
"attn_pdrop": 0.1,
|
13 |
+
"average_logits": false,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"cross_attention_hidden_size": null,
|
19 |
+
"decoder_start_token_id": null,
|
20 |
+
"diversity_penalty": 0.0,
|
21 |
+
"do_sample": false,
|
22 |
+
"early_stopping": false,
|
23 |
+
"embd_pdrop": 0.1,
|
24 |
+
"encoder_no_repeat_ngram_size": 0,
|
25 |
+
"eos_token_id": 1,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"head_locations": [
|
31 |
+
3
|
32 |
+
],
|
33 |
+
"head_weights": [
|
34 |
+
0.6,
|
35 |
+
0.4
|
36 |
+
],
|
37 |
+
"id2label": {
|
38 |
+
"0": "LABEL_0",
|
39 |
+
"1": "LABEL_1"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"is_decoder": true,
|
43 |
+
"is_encoder_decoder": false,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1
|
47 |
+
},
|
48 |
+
"layer_norm_epsilon": 1e-05,
|
49 |
+
"length_penalty": 1.0,
|
50 |
+
"max_length": 20,
|
51 |
+
"min_length": 0,
|
52 |
+
"model_type": "gpt2-multi-head",
|
53 |
+
"n_embd": 256,
|
54 |
+
"n_head": 4,
|
55 |
+
"n_inner": 2048,
|
56 |
+
"n_layer": 6,
|
57 |
+
"n_positions": 1024,
|
58 |
+
"no_repeat_ngram_size": 0,
|
59 |
+
"num_beam_groups": 1,
|
60 |
+
"num_beams": 1,
|
61 |
+
"num_return_sequences": 1,
|
62 |
+
"output_attentions": false,
|
63 |
+
"output_hidden_states": false,
|
64 |
+
"output_scores": false,
|
65 |
+
"pad_token_id": null,
|
66 |
+
"pos_emb_fixed": true,
|
67 |
+
"prefix": null,
|
68 |
+
"problem_type": null,
|
69 |
+
"pruned_heads": {},
|
70 |
+
"remove_invalid_values": false,
|
71 |
+
"reorder_and_upcast_attn": false,
|
72 |
+
"repetition_penalty": 1.0,
|
73 |
+
"resid_pdrop": 0.1,
|
74 |
+
"return_dict": true,
|
75 |
+
"return_dict_in_generate": false,
|
76 |
+
"scale_attn_by_inverse_layer_idx": false,
|
77 |
+
"scale_attn_weights": true,
|
78 |
+
"sep_token_id": null,
|
79 |
+
"summary_activation": null,
|
80 |
+
"summary_first_dropout": 0.1,
|
81 |
+
"summary_proj_to_labels": true,
|
82 |
+
"summary_type": "cls_index",
|
83 |
+
"summary_use_proj": true,
|
84 |
+
"suppress_tokens": null,
|
85 |
+
"task_specific_params": null,
|
86 |
+
"temperature": 1.0,
|
87 |
+
"tf_legacy_loss": false,
|
88 |
+
"tie_additional_weights": false,
|
89 |
+
"tie_encoder_decoder": false,
|
90 |
+
"tie_word_embeddings": false,
|
91 |
+
"tokenizer_class": null,
|
92 |
+
"top_k": 50,
|
93 |
+
"top_p": 1.0,
|
94 |
+
"torch_dtype": null,
|
95 |
+
"torchscript": false,
|
96 |
+
"typical_p": 1.0,
|
97 |
+
"use_bfloat16": false,
|
98 |
+
"use_cache": true,
|
99 |
+
"vocab_size": 1000
|
100 |
+
},
|
101 |
+
"decoder_start_token_id": 0,
|
102 |
+
"encoder": {
|
103 |
+
"_name_or_path": "Lakoc/fisher_ebranchformer_enc_12_layers_fixed",
|
104 |
+
"activation_dropout": 0.1,
|
105 |
+
"adapter_attn_dim": null,
|
106 |
+
"adapter_kernel_size": 3,
|
107 |
+
"adapter_stride": 2,
|
108 |
+
"add_adapter": false,
|
109 |
+
"add_cross_attention": false,
|
110 |
+
"apply_spec_augment": false,
|
111 |
+
"architectures": null,
|
112 |
+
"attention_dropout": 0.1,
|
113 |
+
"bad_words_ids": null,
|
114 |
+
"begin_suppress_tokens": null,
|
115 |
+
"bos_token_id": 1,
|
116 |
+
"chunk_size_feed_forward": 0,
|
117 |
+
"classifier_proj_size": 256,
|
118 |
+
"codevector_dim": 256,
|
119 |
+
"conformer_conv_dropout": 0.1,
|
120 |
+
"contrastive_logits_temperature": 0.1,
|
121 |
+
"conv_bias": false,
|
122 |
+
"conv_depthwise_kernel_size": 31,
|
123 |
+
"conv_dim": [
|
124 |
+
256,
|
125 |
+
256
|
126 |
+
],
|
127 |
+
"conv_kernel": [
|
128 |
+
3,
|
129 |
+
3
|
130 |
+
],
|
131 |
+
"conv_padding": [
|
132 |
+
1,
|
133 |
+
1
|
134 |
+
],
|
135 |
+
"conv_stride": [
|
136 |
+
2,
|
137 |
+
2
|
138 |
+
],
|
139 |
+
"cross_attention_hidden_size": null,
|
140 |
+
"csgu_activation": "identity",
|
141 |
+
"csgu_conv_dropout": 0.1,
|
142 |
+
"csgu_kernel_size": 31,
|
143 |
+
"csgu_use_linear_after_conv": false,
|
144 |
+
"ctc_loss_reduction": "mean",
|
145 |
+
"ctc_zero_infinity": true,
|
146 |
+
"decoder_start_token_id": null,
|
147 |
+
"diversity_loss_weight": 0.1,
|
148 |
+
"diversity_penalty": 0.0,
|
149 |
+
"do_sample": false,
|
150 |
+
"do_stable_layer_norm": false,
|
151 |
+
"early_stopping": false,
|
152 |
+
"encoder_no_repeat_ngram_size": 0,
|
153 |
+
"eos_token_id": 2,
|
154 |
+
"exponential_decay_length_penalty": null,
|
155 |
+
"fe_position_embeddings": false,
|
156 |
+
"feat_extract_activation": "gelu",
|
157 |
+
"feat_extract_norm": "group",
|
158 |
+
"feat_proj_dropout": 0.0,
|
159 |
+
"feat_quantizer_dropout": 0.0,
|
160 |
+
"final_dropout": 0.1,
|
161 |
+
"finetuning_task": null,
|
162 |
+
"forced_bos_token_id": null,
|
163 |
+
"forced_eos_token_id": null,
|
164 |
+
"hidden_act": "gelu",
|
165 |
+
"hidden_dropout": 0.1,
|
166 |
+
"hidden_size": 256,
|
167 |
+
"id2label": {
|
168 |
+
"0": "LABEL_0",
|
169 |
+
"1": "LABEL_1"
|
170 |
+
},
|
171 |
+
"initializer_range": 0.02,
|
172 |
+
"intermediate_size": 1024,
|
173 |
+
"is_causal": false,
|
174 |
+
"is_decoder": false,
|
175 |
+
"is_encoder_decoder": false,
|
176 |
+
"label2id": {
|
177 |
+
"LABEL_0": 0,
|
178 |
+
"LABEL_1": 1
|
179 |
+
},
|
180 |
+
"layer_norm_eps": 1e-05,
|
181 |
+
"layerdrop": 0.0,
|
182 |
+
"length_penalty": 1.0,
|
183 |
+
"mask_feature_length": 10,
|
184 |
+
"mask_feature_min_masks": 0,
|
185 |
+
"mask_feature_prob": 0.0,
|
186 |
+
"mask_time_length": 10,
|
187 |
+
"mask_time_min_masks": 2,
|
188 |
+
"mask_time_prob": 0.05,
|
189 |
+
"max_length": 20,
|
190 |
+
"max_source_positions": 1024,
|
191 |
+
"merge_conv_kernel": 31,
|
192 |
+
"min_length": 0,
|
193 |
+
"model_type": "wav2vec2-ebranchformer",
|
194 |
+
"no_repeat_ngram_size": 0,
|
195 |
+
"num_adapter_layers": 3,
|
196 |
+
"num_attention_heads": 4,
|
197 |
+
"num_beam_groups": 1,
|
198 |
+
"num_beams": 1,
|
199 |
+
"num_codevector_groups": 2,
|
200 |
+
"num_codevectors_per_group": 320,
|
201 |
+
"num_conv_pos_embedding_groups": 16,
|
202 |
+
"num_conv_pos_embeddings": 128,
|
203 |
+
"num_fbanks": 80,
|
204 |
+
"num_feat_extract_layers": 2,
|
205 |
+
"num_hidden_layers": 12,
|
206 |
+
"num_mel_bins": 80,
|
207 |
+
"num_negatives": 100,
|
208 |
+
"num_return_sequences": 1,
|
209 |
+
"output_attentions": false,
|
210 |
+
"output_hidden_size": 256,
|
211 |
+
"output_hidden_states": false,
|
212 |
+
"output_scores": false,
|
213 |
+
"pad_token_id": 3,
|
214 |
+
"position_embeddings_type": "relative",
|
215 |
+
"prefix": null,
|
216 |
+
"problem_type": null,
|
217 |
+
"proj_codevector_dim": 256,
|
218 |
+
"pruned_heads": {},
|
219 |
+
"remove_invalid_values": false,
|
220 |
+
"repetition_penalty": 1.0,
|
221 |
+
"return_dict": true,
|
222 |
+
"return_dict_in_generate": false,
|
223 |
+
"rotary_embedding_base": 10000,
|
224 |
+
"sep_token_id": null,
|
225 |
+
"suppress_tokens": null,
|
226 |
+
"task_specific_params": null,
|
227 |
+
"tdnn_dilation": [
|
228 |
+
1,
|
229 |
+
2,
|
230 |
+
3,
|
231 |
+
1,
|
232 |
+
1
|
233 |
+
],
|
234 |
+
"tdnn_dim": [
|
235 |
+
512,
|
236 |
+
512,
|
237 |
+
512,
|
238 |
+
512,
|
239 |
+
1500
|
240 |
+
],
|
241 |
+
"tdnn_kernel": [
|
242 |
+
5,
|
243 |
+
3,
|
244 |
+
3,
|
245 |
+
1,
|
246 |
+
1
|
247 |
+
],
|
248 |
+
"temperature": 1.0,
|
249 |
+
"tf_legacy_loss": false,
|
250 |
+
"tie_encoder_decoder": false,
|
251 |
+
"tie_word_embeddings": true,
|
252 |
+
"tokenizer_class": null,
|
253 |
+
"top_k": 50,
|
254 |
+
"top_p": 1.0,
|
255 |
+
"torch_dtype": null,
|
256 |
+
"torchscript": false,
|
257 |
+
"typical_p": 1.0,
|
258 |
+
"use_bfloat16": false,
|
259 |
+
"use_fbanks": true,
|
260 |
+
"use_macaron_ff": true,
|
261 |
+
"use_weighted_layer_sum": false,
|
262 |
+
"vocab_size": 1000,
|
263 |
+
"xvector_output_dim": 512
|
264 |
+
},
|
265 |
+
"eos_token_id": 1,
|
266 |
+
"is_encoder_decoder": true,
|
267 |
+
"lsm_factor": 0.1,
|
268 |
+
"mask_token_id": 4,
|
269 |
+
"model_type": "joint_aed_ctc_speech-encoder-decoder",
|
270 |
+
"pad_token_id": 3,
|
271 |
+
"shared_lm_head": false,
|
272 |
+
"tie_word_embeddings": false,
|
273 |
+
"torch_dtype": "float32",
|
274 |
+
"transformers_version": "4.40.0.dev0"
|
275 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_eos_space_trick": false,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"ctc_margin": 0,
|
5 |
+
"ctc_weight": 0.0,
|
6 |
+
"decoder_start_token_id": 0,
|
7 |
+
"eos_space_trick_weight": 0.0,
|
8 |
+
"eos_token_id": 1,
|
9 |
+
"lm_model": null,
|
10 |
+
"lm_weight": 0.0,
|
11 |
+
"max_length": 512,
|
12 |
+
"pad_token_id": 3,
|
13 |
+
"space_token_id": -1,
|
14 |
+
"transformers_version": "4.40.0.dev0"
|
15 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d76549a0d7e10e586fdab217fb2431b1e0bcfb5d17f9839a30dd537d3e187303
|
3 |
+
size 144243216
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.47.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.47_hyp.trn
ADDED
The diff for this file is too large to render.
See raw diff
|
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.47_ref.trn
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff64ef1971f96d63c84ef22dd935a383b14e09ebbe15cece61b3429bfa7b8760
|
3 |
+
size 5816
|