bigmorning
commited on
Commit
•
96d544d
1
Parent(s):
70c0069
Upload TFWhisperForConditionalGeneration
Browse files- README.md +101 -0
- config.json +64 -0
- generation_config.json +117 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_input_decoder_shift_r_labels_with_force__0045
|
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_input_decoder_shift_r_labels_with_force__0045
|
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: 0.1194
|
19 |
+
- Train Accuracy: 0.0334
|
20 |
+
- Train Wermet: 0.3137
|
21 |
+
- Validation Loss: 0.7596
|
22 |
+
- Validation Accuracy: 0.0207
|
23 |
+
- Validation Wermet: 0.5479
|
24 |
+
- Epoch: 44
|
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 |
+
| 5.6249 | 0.0091 | 1.7162 | 4.2965 | 0.0094 | 0.9447 | 0 |
|
51 |
+
| 4.9223 | 0.0099 | 0.9041 | 4.1562 | 0.0097 | 0.9327 | 1 |
|
52 |
+
| 4.6814 | 0.0107 | 0.8376 | 3.9245 | 0.0103 | 0.8927 | 2 |
|
53 |
+
| 4.4407 | 0.0114 | 0.8311 | 3.7252 | 0.0107 | 0.8775 | 3 |
|
54 |
+
| 4.2445 | 0.0119 | 0.8228 | 3.6283 | 0.0108 | 0.8695 | 4 |
|
55 |
+
| 4.0889 | 0.0123 | 0.8067 | 3.5310 | 0.0110 | 0.8916 | 5 |
|
56 |
+
| 3.9575 | 0.0127 | 0.7908 | 3.4478 | 0.0113 | 0.8407 | 6 |
|
57 |
+
| 3.8547 | 0.0130 | 0.7781 | 3.4227 | 0.0113 | 0.8670 | 7 |
|
58 |
+
| 3.7599 | 0.0133 | 0.7654 | 3.3519 | 0.0115 | 0.8375 | 8 |
|
59 |
+
| 3.6763 | 0.0136 | 0.7543 | 3.3183 | 0.0116 | 0.8678 | 9 |
|
60 |
+
| 3.6006 | 0.0138 | 0.7421 | 3.2581 | 0.0117 | 0.8120 | 10 |
|
61 |
+
| 3.5300 | 0.0140 | 0.7296 | 3.2415 | 0.0118 | 0.8257 | 11 |
|
62 |
+
| 3.4554 | 0.0143 | 0.7179 | 3.2163 | 0.0119 | 0.8078 | 12 |
|
63 |
+
| 3.3930 | 0.0145 | 0.7057 | 3.1612 | 0.0121 | 0.7758 | 13 |
|
64 |
+
| 3.3218 | 0.0148 | 0.6946 | 3.1357 | 0.0122 | 0.7760 | 14 |
|
65 |
+
| 3.2424 | 0.0151 | 0.6806 | 3.0812 | 0.0123 | 0.7639 | 15 |
|
66 |
+
| 3.1577 | 0.0155 | 0.6633 | 3.0193 | 0.0126 | 0.7428 | 16 |
|
67 |
+
| 3.0655 | 0.0159 | 0.6454 | 2.9643 | 0.0128 | 0.7423 | 17 |
|
68 |
+
| 2.9579 | 0.0164 | 0.6271 | 2.8510 | 0.0132 | 0.7103 | 18 |
|
69 |
+
| 2.8149 | 0.0170 | 0.6022 | 2.7020 | 0.0136 | 0.6811 | 19 |
|
70 |
+
| 2.6475 | 0.0178 | 0.5775 | 2.5406 | 0.0142 | 0.6495 | 20 |
|
71 |
+
| 2.4340 | 0.0189 | 0.5451 | 2.3364 | 0.0149 | 0.6166 | 21 |
|
72 |
+
| 2.2002 | 0.0200 | 0.5065 | 2.1300 | 0.0155 | 0.5766 | 22 |
|
73 |
+
| 1.9511 | 0.0213 | 0.4658 | 1.9335 | 0.0162 | 0.5419 | 23 |
|
74 |
+
| 1.6777 | 0.0228 | 0.4184 | 1.7327 | 0.0169 | 0.5071 | 24 |
|
75 |
+
| 1.4282 | 0.0243 | 0.3754 | 1.5461 | 0.0176 | 0.4669 | 25 |
|
76 |
+
| 1.2219 | 0.0255 | 0.3365 | 1.4027 | 0.0181 | 0.4326 | 26 |
|
77 |
+
| 1.0535 | 0.0265 | 0.3016 | 1.2979 | 0.0185 | 0.4134 | 27 |
|
78 |
+
| 0.9205 | 0.0274 | 0.2731 | 1.1891 | 0.0189 | 0.3843 | 28 |
|
79 |
+
| 0.8079 | 0.0281 | 0.2453 | 1.1135 | 0.0192 | 0.3659 | 29 |
|
80 |
+
| 0.7140 | 0.0288 | 0.2218 | 1.0532 | 0.0195 | 0.3495 | 30 |
|
81 |
+
| 0.6318 | 0.0293 | 0.1975 | 0.9976 | 0.0197 | 0.3351 | 31 |
|
82 |
+
| 0.5623 | 0.0298 | 0.1770 | 0.9571 | 0.0199 | 0.3256 | 32 |
|
83 |
+
| 0.4990 | 0.0303 | 0.1582 | 0.9184 | 0.0200 | 0.3147 | 33 |
|
84 |
+
| 0.4444 | 0.0307 | 0.1424 | 0.8865 | 0.0202 | 0.3062 | 34 |
|
85 |
+
| 0.3949 | 0.0311 | 0.1260 | 0.8532 | 0.0203 | 0.2968 | 35 |
|
86 |
+
| 0.3505 | 0.0314 | 0.1118 | 0.8333 | 0.0204 | 0.2898 | 36 |
|
87 |
+
| 0.3104 | 0.0317 | 0.0988 | 0.8245 | 0.0204 | 0.2881 | 37 |
|
88 |
+
| 0.2743 | 0.0321 | 0.0886 | 0.8014 | 0.0205 | 0.2825 | 38 |
|
89 |
+
| 0.2428 | 0.0323 | 0.0842 | 0.7944 | 0.0206 | 0.2794 | 39 |
|
90 |
+
| 0.2120 | 0.0326 | 0.0880 | 0.7742 | 0.0206 | 0.2762 | 40 |
|
91 |
+
| 0.1863 | 0.0328 | 0.1289 | 0.7744 | 0.0206 | 0.2863 | 41 |
|
92 |
+
| 0.1621 | 0.0330 | 0.1792 | 0.7683 | 0.0207 | 0.2873 | 42 |
|
93 |
+
| 0.1390 | 0.0332 | 0.1918 | 0.7664 | 0.0207 | 0.4006 | 43 |
|
94 |
+
| 0.1194 | 0.0334 | 0.3137 | 0.7596 | 0.0207 | 0.5479 | 44 |
|
95 |
+
|
96 |
+
|
97 |
+
### Framework versions
|
98 |
+
|
99 |
+
- Transformers 4.34.0.dev0
|
100 |
+
- TensorFlow 2.13.0
|
101 |
+
- 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": 50257,
|
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 sha256:2b781f5a680add038ad88ffd4f0c507999e79e5e3d2113f4b4280122bfce0e7f
|
3 |
+
size 151253960
|