bigmorning
commited on
Commit
•
77cd8a6
1
Parent(s):
1191421
Upload TFWhisperForConditionalGeneration
Browse files- README.md +88 -0
- config.json +64 -0
- generation_config.json +117 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_charsplit_new_0032
|
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_0032
|
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: 0.0043
|
19 |
+
- Train Accuracy: 0.0795
|
20 |
+
- Train Wermet: 10.9497
|
21 |
+
- Validation Loss: 0.4525
|
22 |
+
- Validation Accuracy: 0.0761
|
23 |
+
- Validation Wermet: 9.3202
|
24 |
+
- Epoch: 31
|
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 |
+
| 0.8733 | 0.0602 | 13.0686 | 0.6470 | 0.0676 | 11.4066 | 0 |
|
51 |
+
| 0.5740 | 0.0666 | 12.7778 | 0.5113 | 0.0706 | 11.1022 | 1 |
|
52 |
+
| 0.4553 | 0.0692 | 12.2404 | 0.4371 | 0.0723 | 10.9105 | 2 |
|
53 |
+
| 0.3813 | 0.0708 | 11.9157 | 0.3935 | 0.0733 | 9.4615 | 3 |
|
54 |
+
| 0.3292 | 0.0720 | 11.5732 | 0.3630 | 0.0740 | 9.9885 | 4 |
|
55 |
+
| 0.2886 | 0.0729 | 11.5171 | 0.3403 | 0.0745 | 9.8042 | 5 |
|
56 |
+
| 0.2561 | 0.0736 | 11.3173 | 0.3256 | 0.0749 | 9.9431 | 6 |
|
57 |
+
| 0.2282 | 0.0743 | 11.7308 | 0.3159 | 0.0752 | 9.2086 | 7 |
|
58 |
+
| 0.2036 | 0.0748 | 11.4503 | 0.3071 | 0.0754 | 9.5236 | 8 |
|
59 |
+
| 0.1820 | 0.0754 | 11.7175 | 0.3005 | 0.0756 | 10.0755 | 9 |
|
60 |
+
| 0.1628 | 0.0758 | 11.7056 | 0.2993 | 0.0757 | 9.9497 | 10 |
|
61 |
+
| 0.1450 | 0.0762 | 11.7637 | 0.2971 | 0.0758 | 10.1481 | 11 |
|
62 |
+
| 0.1287 | 0.0766 | 11.8509 | 0.3029 | 0.0759 | 10.2042 | 12 |
|
63 |
+
| 0.1140 | 0.0770 | 12.1100 | 0.3004 | 0.0760 | 10.3873 | 13 |
|
64 |
+
| 0.0998 | 0.0773 | 11.9502 | 0.3025 | 0.0761 | 10.7066 | 14 |
|
65 |
+
| 0.0872 | 0.0777 | 12.3196 | 0.3129 | 0.0759 | 10.7707 | 15 |
|
66 |
+
| 0.0760 | 0.0779 | 12.2637 | 0.3142 | 0.0761 | 10.2638 | 16 |
|
67 |
+
| 0.0651 | 0.0782 | 12.1215 | 0.3192 | 0.0761 | 10.0750 | 17 |
|
68 |
+
| 0.0547 | 0.0785 | 12.0551 | 0.3294 | 0.0761 | 10.4732 | 18 |
|
69 |
+
| 0.0463 | 0.0787 | 11.9677 | 0.3402 | 0.0760 | 10.2814 | 19 |
|
70 |
+
| 0.0386 | 0.0789 | 11.6855 | 0.3517 | 0.0760 | 10.0599 | 20 |
|
71 |
+
| 0.0318 | 0.0790 | 11.6314 | 0.3628 | 0.0760 | 9.6652 | 21 |
|
72 |
+
| 0.0262 | 0.0792 | 11.4603 | 0.3728 | 0.0760 | 10.0035 | 22 |
|
73 |
+
| 0.0224 | 0.0792 | 11.4330 | 0.3824 | 0.0760 | 9.1995 | 23 |
|
74 |
+
| 0.0181 | 0.0793 | 11.3124 | 0.3982 | 0.0759 | 9.8710 | 24 |
|
75 |
+
| 0.0142 | 0.0794 | 11.3562 | 0.4057 | 0.0760 | 9.6831 | 25 |
|
76 |
+
| 0.0118 | 0.0794 | 11.0532 | 0.4207 | 0.0759 | 9.7227 | 26 |
|
77 |
+
| 0.0101 | 0.0794 | 11.2963 | 0.4282 | 0.0760 | 9.5792 | 27 |
|
78 |
+
| 0.0114 | 0.0794 | 11.3093 | 0.4431 | 0.0758 | 9.5545 | 28 |
|
79 |
+
| 0.0109 | 0.0794 | 11.4214 | 0.4419 | 0.0760 | 9.4377 | 29 |
|
80 |
+
| 0.0084 | 0.0794 | 10.9143 | 0.4474 | 0.0760 | 9.3668 | 30 |
|
81 |
+
| 0.0043 | 0.0795 | 10.9497 | 0.4525 | 0.0761 | 9.3202 | 31 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.32.0.dev0
|
87 |
+
- TensorFlow 2.12.0
|
88 |
+
- 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": "4.32.0.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 sha256:93e105eb39ac007e4ab75d1dae007ec7ed789c3bc21d6b72c2c892cab797a35b
|
3 |
+
size 151253960
|