bigmorning
commited on
Commit
•
247b4fc
1
Parent(s):
6a7a286
Upload TFWhisperForConditionalGeneration
Browse files- README.md +102 -0
- config.json +64 -0
- generation_config.json +117 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bigmorning/whisper_charsplit_new_round2__0061
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: whisper_charsplit_new_round3__0046
|
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_charsplit_new_round3__0046
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bigmorning/whisper_charsplit_new_round2__0061](https://huggingface.co/bigmorning/whisper_charsplit_new_round2__0061) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.0000
|
19 |
+
- Train Accuracy: 0.0795
|
20 |
+
- Train Wermet: 7.7766
|
21 |
+
- Validation Loss: 0.5639
|
22 |
+
- Validation Accuracy: 0.0772
|
23 |
+
- Validation Wermet: 6.8982
|
24 |
+
- Epoch: 45
|
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 |
+
| 0.0009 | 0.0795 | 7.9492 | 0.5730 | 0.0769 | 7.2856 | 0 |
|
51 |
+
| 0.0015 | 0.0795 | 8.4221 | 0.5756 | 0.0769 | 7.1487 | 1 |
|
52 |
+
| 0.0012 | 0.0795 | 7.8476 | 0.5699 | 0.0769 | 6.5976 | 2 |
|
53 |
+
| 0.0010 | 0.0795 | 7.6843 | 0.5740 | 0.0769 | 6.9513 | 3 |
|
54 |
+
| 0.0014 | 0.0795 | 8.0796 | 0.5763 | 0.0768 | 7.4043 | 4 |
|
55 |
+
| 0.0019 | 0.0795 | 7.7274 | 0.5724 | 0.0769 | 6.4922 | 5 |
|
56 |
+
| 0.0008 | 0.0795 | 7.3468 | 0.5734 | 0.0769 | 6.1909 | 6 |
|
57 |
+
| 0.0009 | 0.0795 | 7.2393 | 0.5816 | 0.0769 | 6.5734 | 7 |
|
58 |
+
| 0.0010 | 0.0795 | 7.5822 | 0.5755 | 0.0769 | 6.6613 | 8 |
|
59 |
+
| 0.0004 | 0.0795 | 7.3807 | 0.5698 | 0.0770 | 7.0671 | 9 |
|
60 |
+
| 0.0001 | 0.0795 | 7.7157 | 0.5681 | 0.0771 | 6.8391 | 10 |
|
61 |
+
| 0.0001 | 0.0795 | 7.7540 | 0.5725 | 0.0771 | 6.9281 | 11 |
|
62 |
+
| 0.0001 | 0.0795 | 7.7721 | 0.5726 | 0.0771 | 6.8911 | 12 |
|
63 |
+
| 0.0000 | 0.0795 | 7.8163 | 0.5721 | 0.0771 | 6.8876 | 13 |
|
64 |
+
| 0.0000 | 0.0795 | 7.7745 | 0.5741 | 0.0771 | 6.8770 | 14 |
|
65 |
+
| 0.0000 | 0.0795 | 7.7277 | 0.5752 | 0.0771 | 6.8671 | 15 |
|
66 |
+
| 0.0000 | 0.0795 | 7.7355 | 0.5765 | 0.0771 | 6.8447 | 16 |
|
67 |
+
| 0.0000 | 0.0795 | 7.7109 | 0.5784 | 0.0771 | 6.8560 | 17 |
|
68 |
+
| 0.0000 | 0.0795 | 7.7427 | 0.5796 | 0.0771 | 6.8406 | 18 |
|
69 |
+
| 0.0003 | 0.0795 | 7.6709 | 0.6610 | 0.0762 | 7.0119 | 19 |
|
70 |
+
| 0.0115 | 0.0793 | 8.3288 | 0.5580 | 0.0769 | 7.1457 | 20 |
|
71 |
+
| 0.0013 | 0.0795 | 8.2537 | 0.5574 | 0.0770 | 6.7708 | 21 |
|
72 |
+
| 0.0004 | 0.0795 | 8.0507 | 0.5619 | 0.0770 | 7.0678 | 22 |
|
73 |
+
| 0.0003 | 0.0795 | 8.0534 | 0.5593 | 0.0771 | 7.0433 | 23 |
|
74 |
+
| 0.0002 | 0.0795 | 8.1738 | 0.5604 | 0.0771 | 7.1617 | 24 |
|
75 |
+
| 0.0001 | 0.0795 | 8.1494 | 0.5589 | 0.0771 | 7.1609 | 25 |
|
76 |
+
| 0.0000 | 0.0795 | 8.2151 | 0.5614 | 0.0771 | 7.1972 | 26 |
|
77 |
+
| 0.0000 | 0.0795 | 8.2332 | 0.5633 | 0.0771 | 7.1736 | 27 |
|
78 |
+
| 0.0000 | 0.0795 | 8.2573 | 0.5648 | 0.0771 | 7.2086 | 28 |
|
79 |
+
| 0.0000 | 0.0795 | 8.2571 | 0.5667 | 0.0771 | 7.1787 | 29 |
|
80 |
+
| 0.0000 | 0.0795 | 8.2607 | 0.5689 | 0.0771 | 7.2107 | 30 |
|
81 |
+
| 0.0000 | 0.0795 | 8.2992 | 0.5700 | 0.0772 | 7.2006 | 31 |
|
82 |
+
| 0.0000 | 0.0795 | 8.3059 | 0.5721 | 0.0772 | 7.2341 | 32 |
|
83 |
+
| 0.0000 | 0.0795 | 8.2872 | 0.5744 | 0.0772 | 7.2069 | 33 |
|
84 |
+
| 0.0080 | 0.0794 | 8.3693 | 0.5947 | 0.0762 | 7.3034 | 34 |
|
85 |
+
| 0.0063 | 0.0794 | 8.2517 | 0.5491 | 0.0769 | 7.1324 | 35 |
|
86 |
+
| 0.0008 | 0.0795 | 7.9115 | 0.5447 | 0.0771 | 6.9422 | 36 |
|
87 |
+
| 0.0002 | 0.0795 | 7.6265 | 0.5471 | 0.0771 | 6.8107 | 37 |
|
88 |
+
| 0.0001 | 0.0795 | 7.6685 | 0.5493 | 0.0771 | 6.6914 | 38 |
|
89 |
+
| 0.0001 | 0.0795 | 7.6100 | 0.5515 | 0.0771 | 6.7738 | 39 |
|
90 |
+
| 0.0000 | 0.0795 | 7.6623 | 0.5535 | 0.0771 | 6.7829 | 40 |
|
91 |
+
| 0.0000 | 0.0795 | 7.6768 | 0.5556 | 0.0771 | 6.8287 | 41 |
|
92 |
+
| 0.0000 | 0.0795 | 7.7199 | 0.5578 | 0.0772 | 6.8398 | 42 |
|
93 |
+
| 0.0000 | 0.0795 | 7.7423 | 0.5600 | 0.0772 | 6.8518 | 43 |
|
94 |
+
| 0.0000 | 0.0795 | 7.7561 | 0.5617 | 0.0772 | 6.8898 | 44 |
|
95 |
+
| 0.0000 | 0.0795 | 7.7766 | 0.5639 | 0.0772 | 6.8982 | 45 |
|
96 |
+
|
97 |
+
|
98 |
+
### Framework versions
|
99 |
+
|
100 |
+
- Transformers 4.32.0.dev0
|
101 |
+
- TensorFlow 2.12.0
|
102 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigmorning/whisper_charsplit_new_round2__0061",
|
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": "4.32.0.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": "4.32.0.dev0"
|
117 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab44c51ec96dfb23c2449eb573445dda89f177e9ea6463ac2ce1abddffe84654
|
3 |
+
size 151253960
|