bigmorning
commited on
Commit
•
81653ce
1
Parent(s):
24b7e8a
Upload TFWhisperForConditionalGeneration
Browse files- README.md +121 -0
- config.json +64 -0
- generation_config.json +117 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: openai/whisper-tiny
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: whisper_4_with_init_sun__0065
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# whisper_4_with_init_sun__0065
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.4037
|
19 |
+
- Train Accuracy: 0.0324
|
20 |
+
- Train Wermet: 0.0912
|
21 |
+
- Validation Loss: 1.1798
|
22 |
+
- Validation Accuracy: 0.0206
|
23 |
+
- Validation Wermet: 0.3272
|
24 |
+
- Epoch: 64
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
44 |
+
- training_precision: float32
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|
49 |
+
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
|
50 |
+
| 5.3333 | 0.0111 | 1.3132 | 3.9675 | 0.0114 | 0.9339 | 0 |
|
51 |
+
| 4.7131 | 0.0116 | 0.8607 | 3.9360 | 0.0114 | 0.9503 | 1 |
|
52 |
+
| 4.6717 | 0.0117 | 0.8449 | 3.9196 | 0.0113 | 0.9768 | 2 |
|
53 |
+
| 4.6474 | 0.0117 | 0.8338 | 3.9039 | 0.0114 | 0.9557 | 3 |
|
54 |
+
| 4.6273 | 0.0118 | 0.8243 | 3.8721 | 0.0115 | 0.9414 | 4 |
|
55 |
+
| 4.6101 | 0.0118 | 0.8167 | 3.8629 | 0.0116 | 0.9156 | 5 |
|
56 |
+
| 4.5912 | 0.0119 | 0.7985 | 3.8361 | 0.0116 | 0.8988 | 6 |
|
57 |
+
| 4.5645 | 0.0120 | 0.7753 | 3.8298 | 0.0116 | 0.9045 | 7 |
|
58 |
+
| 4.5386 | 0.0121 | 0.7558 | 3.7904 | 0.0118 | 0.8426 | 8 |
|
59 |
+
| 4.5075 | 0.0122 | 0.7405 | 3.7472 | 0.0119 | 0.8103 | 9 |
|
60 |
+
| 4.4586 | 0.0124 | 0.7255 | 3.7163 | 0.0120 | 0.8189 | 10 |
|
61 |
+
| 4.3978 | 0.0126 | 0.7174 | 3.6168 | 0.0122 | 0.8163 | 11 |
|
62 |
+
| 4.3031 | 0.0128 | 0.7107 | 3.4956 | 0.0125 | 0.7847 | 12 |
|
63 |
+
| 4.1606 | 0.0133 | 0.7025 | 3.3414 | 0.0128 | 0.7897 | 13 |
|
64 |
+
| 3.9636 | 0.0138 | 0.6991 | 3.1311 | 0.0133 | 0.7495 | 14 |
|
65 |
+
| 3.7290 | 0.0145 | 0.6827 | 2.8892 | 0.0139 | 0.7292 | 15 |
|
66 |
+
| 3.4993 | 0.0152 | 0.6643 | 2.7195 | 0.0143 | 0.7129 | 16 |
|
67 |
+
| 3.2810 | 0.0159 | 0.6448 | 2.5418 | 0.0148 | 0.6803 | 17 |
|
68 |
+
| 3.0604 | 0.0167 | 0.6182 | 2.3572 | 0.0153 | 0.6538 | 18 |
|
69 |
+
| 2.8748 | 0.0174 | 0.5946 | 2.2575 | 0.0156 | 0.6337 | 19 |
|
70 |
+
| 2.6889 | 0.0181 | 0.5699 | 2.0988 | 0.0162 | 0.6016 | 20 |
|
71 |
+
| 2.5493 | 0.0187 | 0.5449 | 1.9878 | 0.0166 | 0.5834 | 21 |
|
72 |
+
| 2.3921 | 0.0194 | 0.5207 | 1.9029 | 0.0168 | 0.5597 | 22 |
|
73 |
+
| 2.2491 | 0.0201 | 0.4987 | 1.8642 | 0.0169 | 0.5409 | 23 |
|
74 |
+
| 2.1254 | 0.0207 | 0.4766 | 1.7354 | 0.0175 | 0.5231 | 24 |
|
75 |
+
| 1.9980 | 0.0213 | 0.4552 | 1.6661 | 0.0178 | 0.5049 | 25 |
|
76 |
+
| 1.9147 | 0.0217 | 0.4382 | 1.6140 | 0.0180 | 0.4921 | 26 |
|
77 |
+
| 1.8008 | 0.0223 | 0.4196 | 1.5652 | 0.0182 | 0.4742 | 27 |
|
78 |
+
| 1.7185 | 0.0228 | 0.4028 | 1.5159 | 0.0184 | 0.4632 | 28 |
|
79 |
+
| 1.6401 | 0.0232 | 0.3867 | 1.4891 | 0.0185 | 0.4548 | 29 |
|
80 |
+
| 1.5786 | 0.0235 | 0.3728 | 1.5141 | 0.0183 | 0.4548 | 30 |
|
81 |
+
| 1.4950 | 0.0241 | 0.3582 | 1.4345 | 0.0188 | 0.4340 | 31 |
|
82 |
+
| 1.4323 | 0.0244 | 0.3448 | 1.3694 | 0.0191 | 0.4226 | 32 |
|
83 |
+
| 1.3495 | 0.0250 | 0.3319 | 1.3780 | 0.0190 | 0.4172 | 33 |
|
84 |
+
| 1.3007 | 0.0253 | 0.3187 | 1.3296 | 0.0193 | 0.4109 | 34 |
|
85 |
+
| 1.2320 | 0.0257 | 0.3074 | 1.3116 | 0.0194 | 0.4029 | 35 |
|
86 |
+
| 1.1836 | 0.0261 | 0.2958 | 1.3025 | 0.0195 | 0.3992 | 36 |
|
87 |
+
| 1.1131 | 0.0266 | 0.2842 | 1.2885 | 0.0195 | 0.3894 | 37 |
|
88 |
+
| 1.0630 | 0.0269 | 0.2730 | 1.2627 | 0.0197 | 0.3850 | 38 |
|
89 |
+
| 1.0189 | 0.0272 | 0.2628 | 1.2633 | 0.0197 | 0.3822 | 39 |
|
90 |
+
| 1.0025 | 0.0273 | 0.2550 | 1.2561 | 0.0197 | 0.3760 | 40 |
|
91 |
+
| 0.9498 | 0.0277 | 0.2445 | 1.2288 | 0.0199 | 0.3710 | 41 |
|
92 |
+
| 0.9027 | 0.0281 | 0.2337 | 1.2188 | 0.0199 | 0.3684 | 42 |
|
93 |
+
| 0.8469 | 0.0286 | 0.2240 | 1.2072 | 0.0200 | 0.3637 | 43 |
|
94 |
+
| 0.8056 | 0.0289 | 0.2153 | 1.2046 | 0.0201 | 0.3599 | 44 |
|
95 |
+
| 0.7761 | 0.0291 | 0.2070 | 1.1989 | 0.0201 | 0.3579 | 45 |
|
96 |
+
| 0.7369 | 0.0295 | 0.1982 | 1.1938 | 0.0202 | 0.3528 | 46 |
|
97 |
+
| 0.7026 | 0.0298 | 0.1902 | 1.1934 | 0.0202 | 0.3508 | 47 |
|
98 |
+
| 0.6976 | 0.0298 | 0.1834 | 1.1803 | 0.0203 | 0.3469 | 48 |
|
99 |
+
| 0.6880 | 0.0298 | 0.1765 | 1.1844 | 0.0203 | 0.3470 | 49 |
|
100 |
+
| 0.6674 | 0.0300 | 0.1702 | 1.1741 | 0.0203 | 0.3446 | 50 |
|
101 |
+
| 0.6099 | 0.0305 | 0.1606 | 1.1753 | 0.0203 | 0.3440 | 51 |
|
102 |
+
| 0.5972 | 0.0306 | 0.1549 | 1.1692 | 0.0204 | 0.3401 | 52 |
|
103 |
+
| 0.5555 | 0.0310 | 0.1475 | 1.1744 | 0.0204 | 0.3382 | 53 |
|
104 |
+
| 0.5275 | 0.0313 | 0.1412 | 1.1743 | 0.0204 | 0.3384 | 54 |
|
105 |
+
| 0.5103 | 0.0315 | 0.1344 | 1.1720 | 0.0205 | 0.3355 | 55 |
|
106 |
+
| 0.5268 | 0.0313 | 0.1308 | 1.1709 | 0.0205 | 0.3343 | 56 |
|
107 |
+
| 0.5060 | 0.0315 | 0.1251 | 1.2090 | 0.0203 | 0.3318 | 57 |
|
108 |
+
| 0.4696 | 0.0318 | 0.1172 | 1.1748 | 0.0205 | 0.3321 | 58 |
|
109 |
+
| 0.4737 | 0.0318 | 0.1136 | 1.1764 | 0.0205 | 0.3313 | 59 |
|
110 |
+
| 0.4749 | 0.0318 | 0.1115 | 1.1684 | 0.0206 | 0.3289 | 60 |
|
111 |
+
| 0.4208 | 0.0323 | 0.1015 | 1.1704 | 0.0206 | 0.3275 | 61 |
|
112 |
+
| 0.3895 | 0.0326 | 0.0958 | 1.1777 | 0.0206 | 0.3286 | 62 |
|
113 |
+
| 0.3721 | 0.0328 | 0.0909 | 1.1754 | 0.0206 | 0.3267 | 63 |
|
114 |
+
| 0.4037 | 0.0324 | 0.0912 | 1.1798 | 0.0206 | 0.3272 | 64 |
|
115 |
+
|
116 |
+
|
117 |
+
### Framework versions
|
118 |
+
|
119 |
+
- Transformers 4.34.0.dev0
|
120 |
+
- TensorFlow 2.13.0
|
121 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-tiny",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
50257
|
12 |
+
],
|
13 |
+
"bos_token_id": 50257,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"d_model": 384,
|
16 |
+
"decoder_attention_heads": 6,
|
17 |
+
"decoder_ffn_dim": 1536,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 4,
|
20 |
+
"decoder_start_token_id": 50258,
|
21 |
+
"dropout": 0.0,
|
22 |
+
"encoder_attention_heads": 6,
|
23 |
+
"encoder_ffn_dim": 1536,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 4,
|
26 |
+
"eos_token_id": 50257,
|
27 |
+
"forced_decoder_ids": [
|
28 |
+
[
|
29 |
+
1,
|
30 |
+
50289
|
31 |
+
],
|
32 |
+
[
|
33 |
+
2,
|
34 |
+
50359
|
35 |
+
],
|
36 |
+
[
|
37 |
+
3,
|
38 |
+
50363
|
39 |
+
]
|
40 |
+
],
|
41 |
+
"init_std": 0.02,
|
42 |
+
"is_encoder_decoder": true,
|
43 |
+
"mask_feature_length": 10,
|
44 |
+
"mask_feature_min_masks": 0,
|
45 |
+
"mask_feature_prob": 0.0,
|
46 |
+
"mask_time_length": 10,
|
47 |
+
"mask_time_min_masks": 2,
|
48 |
+
"mask_time_prob": 0.05,
|
49 |
+
"max_length": 448,
|
50 |
+
"max_source_positions": 1500,
|
51 |
+
"max_target_positions": 448,
|
52 |
+
"median_filter_width": 7,
|
53 |
+
"model_type": "whisper",
|
54 |
+
"num_hidden_layers": 4,
|
55 |
+
"num_mel_bins": 80,
|
56 |
+
"pad_token_id": -100,
|
57 |
+
"scale_embedding": false,
|
58 |
+
"suppress_tokens": [],
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.34.0.dev0",
|
61 |
+
"use_cache": true,
|
62 |
+
"use_weighted_layer_sum": false,
|
63 |
+
"vocab_size": 51865
|
64 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"begin_suppress_tokens": [
|
4 |
+
220,
|
5 |
+
50257
|
6 |
+
],
|
7 |
+
"bos_token_id": 50257,
|
8 |
+
"decoder_start_token_id": 50258,
|
9 |
+
"eos_token_id": 50257,
|
10 |
+
"forced_decoder_ids": [
|
11 |
+
[
|
12 |
+
1,
|
13 |
+
50259
|
14 |
+
],
|
15 |
+
[
|
16 |
+
2,
|
17 |
+
50359
|
18 |
+
],
|
19 |
+
[
|
20 |
+
3,
|
21 |
+
50363
|
22 |
+
]
|
23 |
+
],
|
24 |
+
"max_length": 448,
|
25 |
+
"pad_token_id": 50257,
|
26 |
+
"suppress_tokens": [
|
27 |
+
1,
|
28 |
+
2,
|
29 |
+
7,
|
30 |
+
8,
|
31 |
+
9,
|
32 |
+
10,
|
33 |
+
14,
|
34 |
+
25,
|
35 |
+
26,
|
36 |
+
27,
|
37 |
+
28,
|
38 |
+
29,
|
39 |
+
31,
|
40 |
+
58,
|
41 |
+
59,
|
42 |
+
60,
|
43 |
+
61,
|
44 |
+
62,
|
45 |
+
63,
|
46 |
+
90,
|
47 |
+
91,
|
48 |
+
92,
|
49 |
+
93,
|
50 |
+
359,
|
51 |
+
503,
|
52 |
+
522,
|
53 |
+
542,
|
54 |
+
873,
|
55 |
+
893,
|
56 |
+
902,
|
57 |
+
918,
|
58 |
+
922,
|
59 |
+
931,
|
60 |
+
1350,
|
61 |
+
1853,
|
62 |
+
1982,
|
63 |
+
2460,
|
64 |
+
2627,
|
65 |
+
3246,
|
66 |
+
3253,
|
67 |
+
3268,
|
68 |
+
3536,
|
69 |
+
3846,
|
70 |
+
3961,
|
71 |
+
4183,
|
72 |
+
4667,
|
73 |
+
6585,
|
74 |
+
6647,
|
75 |
+
7273,
|
76 |
+
9061,
|
77 |
+
9383,
|
78 |
+
10428,
|
79 |
+
10929,
|
80 |
+
11938,
|
81 |
+
12033,
|
82 |
+
12331,
|
83 |
+
12562,
|
84 |
+
13793,
|
85 |
+
14157,
|
86 |
+
14635,
|
87 |
+
15265,
|
88 |
+
15618,
|
89 |
+
16553,
|
90 |
+
16604,
|
91 |
+
18362,
|
92 |
+
18956,
|
93 |
+
20075,
|
94 |
+
21675,
|
95 |
+
22520,
|
96 |
+
26130,
|
97 |
+
26161,
|
98 |
+
26435,
|
99 |
+
28279,
|
100 |
+
29464,
|
101 |
+
31650,
|
102 |
+
32302,
|
103 |
+
32470,
|
104 |
+
36865,
|
105 |
+
42863,
|
106 |
+
47425,
|
107 |
+
49870,
|
108 |
+
50254,
|
109 |
+
50258,
|
110 |
+
50358,
|
111 |
+
50359,
|
112 |
+
50360,
|
113 |
+
50361,
|
114 |
+
50362
|
115 |
+
],
|
116 |
+
"transformers_version": "4.34.0.dev0"
|
117 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a4fbc4039355807bbc541038499a1337d30ce3b425f2a05421016496826f10
|
3 |
+
size 151253960
|