bigmorning
commited on
Commit
•
032b679
1
Parent(s):
ae091f2
Upload TFWhisperForConditionalGeneration
Browse files- README.md +95 -0
- config.json +61 -0
- generation_config.json +219 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: whisper_new_split_0040
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# whisper_new_split_0040
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.0024
|
18 |
+
- Train Accuracy: 0.0335
|
19 |
+
- Train Wermet: 33.0830
|
20 |
+
- Validation Loss: 0.4968
|
21 |
+
- Validation Accuracy: 0.0315
|
22 |
+
- Validation Wermet: 35.0547
|
23 |
+
- Epoch: 39
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- 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}
|
43 |
+
- training_precision: float32
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|
48 |
+
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
|
49 |
+
| 5.1027 | 0.0113 | 52.5530 | 4.4267 | 0.0121 | 41.4796 | 0 |
|
50 |
+
| 4.3285 | 0.0126 | 38.6893 | 3.9835 | 0.0145 | 33.6050 | 1 |
|
51 |
+
| 3.4573 | 0.0168 | 30.7714 | 2.5568 | 0.0215 | 31.7559 | 2 |
|
52 |
+
| 2.0878 | 0.0226 | 20.5131 | 1.5738 | 0.0257 | 21.2159 | 3 |
|
53 |
+
| 1.3529 | 0.0258 | 17.4367 | 1.1712 | 0.0276 | 17.7695 | 4 |
|
54 |
+
| 0.9953 | 0.0275 | 18.7308 | 0.9389 | 0.0287 | 20.5259 | 5 |
|
55 |
+
| 0.7852 | 0.0286 | 18.5731 | 0.8074 | 0.0294 | 17.6576 | 6 |
|
56 |
+
| 0.6428 | 0.0293 | 18.2945 | 0.7219 | 0.0298 | 19.9850 | 7 |
|
57 |
+
| 0.5384 | 0.0299 | 18.9258 | 0.6610 | 0.0301 | 18.9327 | 8 |
|
58 |
+
| 0.4565 | 0.0304 | 19.0749 | 0.6117 | 0.0304 | 21.9796 | 9 |
|
59 |
+
| 0.3901 | 0.0308 | 19.2099 | 0.5693 | 0.0306 | 18.0965 | 10 |
|
60 |
+
| 0.3348 | 0.0312 | 20.4777 | 0.5449 | 0.0307 | 19.9518 | 11 |
|
61 |
+
| 0.2877 | 0.0315 | 20.3181 | 0.5232 | 0.0309 | 20.4017 | 12 |
|
62 |
+
| 0.2471 | 0.0318 | 19.2073 | 0.5057 | 0.0310 | 18.7612 | 13 |
|
63 |
+
| 0.2120 | 0.0320 | 19.0961 | 0.4925 | 0.0311 | 22.3187 | 14 |
|
64 |
+
| 0.1809 | 0.0323 | 20.7944 | 0.4849 | 0.0311 | 27.2314 | 15 |
|
65 |
+
| 0.1539 | 0.0325 | 22.0951 | 0.4787 | 0.0312 | 25.2171 | 16 |
|
66 |
+
| 0.1299 | 0.0327 | 22.7652 | 0.4733 | 0.0312 | 22.7492 | 17 |
|
67 |
+
| 0.1087 | 0.0329 | 25.2223 | 0.4701 | 0.0312 | 28.9044 | 18 |
|
68 |
+
| 0.0899 | 0.0330 | 24.8354 | 0.4715 | 0.0313 | 21.1618 | 19 |
|
69 |
+
| 0.0739 | 0.0332 | 25.4987 | 0.4680 | 0.0313 | 29.6304 | 20 |
|
70 |
+
| 0.0604 | 0.0333 | 27.6465 | 0.4693 | 0.0313 | 27.6937 | 21 |
|
71 |
+
| 0.0498 | 0.0333 | 27.7045 | 0.4711 | 0.0313 | 27.5013 | 22 |
|
72 |
+
| 0.0414 | 0.0334 | 28.0547 | 0.4689 | 0.0313 | 29.1776 | 23 |
|
73 |
+
| 0.0327 | 0.0334 | 27.5594 | 0.4718 | 0.0313 | 31.5623 | 24 |
|
74 |
+
| 0.0256 | 0.0335 | 27.3983 | 0.4710 | 0.0313 | 27.1071 | 25 |
|
75 |
+
| 0.0210 | 0.0335 | 24.7398 | 0.4736 | 0.0313 | 30.8282 | 26 |
|
76 |
+
| 0.0165 | 0.0335 | 25.1927 | 0.4773 | 0.0313 | 24.1750 | 27 |
|
77 |
+
| 0.0133 | 0.0335 | 25.6261 | 0.4807 | 0.0313 | 29.9520 | 28 |
|
78 |
+
| 0.0110 | 0.0335 | 25.8127 | 0.4825 | 0.0314 | 27.0813 | 29 |
|
79 |
+
| 0.0171 | 0.0335 | 26.0445 | 0.4858 | 0.0313 | 39.8503 | 30 |
|
80 |
+
| 0.0154 | 0.0335 | 28.6186 | 0.4766 | 0.0314 | 28.4465 | 31 |
|
81 |
+
| 0.0094 | 0.0335 | 27.8978 | 0.4778 | 0.0314 | 28.7775 | 32 |
|
82 |
+
| 0.0071 | 0.0335 | 27.8180 | 0.4775 | 0.0314 | 28.5229 | 33 |
|
83 |
+
| 0.0054 | 0.0335 | 27.4530 | 0.4807 | 0.0315 | 30.3598 | 34 |
|
84 |
+
| 0.0043 | 0.0335 | 27.2908 | 0.4833 | 0.0315 | 29.9185 | 35 |
|
85 |
+
| 0.0036 | 0.0335 | 27.9772 | 0.4870 | 0.0315 | 29.0761 | 36 |
|
86 |
+
| 0.0031 | 0.0335 | 29.0235 | 0.4901 | 0.0315 | 31.1068 | 37 |
|
87 |
+
| 0.0027 | 0.0335 | 28.2433 | 0.4930 | 0.0315 | 30.2512 | 38 |
|
88 |
+
| 0.0024 | 0.0335 | 33.0830 | 0.4968 | 0.0315 | 35.0547 | 39 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.27.0.dev0
|
94 |
+
- TensorFlow 2.11.0
|
95 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"d_model": 384,
|
15 |
+
"decoder_attention_heads": 6,
|
16 |
+
"decoder_ffn_dim": 1536,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 4,
|
19 |
+
"decoder_start_token_id": 50258,
|
20 |
+
"dropout": 0.0,
|
21 |
+
"encoder_attention_heads": 6,
|
22 |
+
"encoder_ffn_dim": 1536,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 4,
|
25 |
+
"eos_token_id": 50257,
|
26 |
+
"forced_decoder_ids": [
|
27 |
+
[
|
28 |
+
1,
|
29 |
+
50289
|
30 |
+
],
|
31 |
+
[
|
32 |
+
2,
|
33 |
+
50359
|
34 |
+
],
|
35 |
+
[
|
36 |
+
3,
|
37 |
+
50363
|
38 |
+
]
|
39 |
+
],
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"mask_feature_length": 10,
|
43 |
+
"mask_feature_min_masks": 0,
|
44 |
+
"mask_feature_prob": 0.0,
|
45 |
+
"mask_time_length": 10,
|
46 |
+
"mask_time_min_masks": 2,
|
47 |
+
"mask_time_prob": 0.05,
|
48 |
+
"max_length": 448,
|
49 |
+
"max_source_positions": 1500,
|
50 |
+
"max_target_positions": 448,
|
51 |
+
"model_type": "whisper",
|
52 |
+
"num_hidden_layers": 4,
|
53 |
+
"num_mel_bins": 80,
|
54 |
+
"pad_token_id": 50257,
|
55 |
+
"scale_embedding": false,
|
56 |
+
"suppress_tokens": [],
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.27.0.dev0",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 51865
|
61 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_suppress_tokens": [
|
3 |
+
220,
|
4 |
+
50257
|
5 |
+
],
|
6 |
+
"bos_token_id": 50257,
|
7 |
+
"decoder_start_token_id": 50258,
|
8 |
+
"eos_token_id": 50257,
|
9 |
+
"forced_decoder_ids": [
|
10 |
+
[
|
11 |
+
1,
|
12 |
+
null
|
13 |
+
],
|
14 |
+
[
|
15 |
+
2,
|
16 |
+
50359
|
17 |
+
]
|
18 |
+
],
|
19 |
+
"is_multilingual": true,
|
20 |
+
"lang_to_id": {
|
21 |
+
"<|af|>": 50327,
|
22 |
+
"<|am|>": 50334,
|
23 |
+
"<|ar|>": 50272,
|
24 |
+
"<|as|>": 50350,
|
25 |
+
"<|az|>": 50304,
|
26 |
+
"<|ba|>": 50355,
|
27 |
+
"<|be|>": 50330,
|
28 |
+
"<|bg|>": 50292,
|
29 |
+
"<|bn|>": 50302,
|
30 |
+
"<|bo|>": 50347,
|
31 |
+
"<|br|>": 50309,
|
32 |
+
"<|bs|>": 50315,
|
33 |
+
"<|ca|>": 50270,
|
34 |
+
"<|cs|>": 50283,
|
35 |
+
"<|cy|>": 50297,
|
36 |
+
"<|da|>": 50285,
|
37 |
+
"<|de|>": 50261,
|
38 |
+
"<|el|>": 50281,
|
39 |
+
"<|en|>": 50259,
|
40 |
+
"<|es|>": 50262,
|
41 |
+
"<|et|>": 50307,
|
42 |
+
"<|eu|>": 50310,
|
43 |
+
"<|fa|>": 50300,
|
44 |
+
"<|fi|>": 50277,
|
45 |
+
"<|fo|>": 50338,
|
46 |
+
"<|fr|>": 50265,
|
47 |
+
"<|gl|>": 50319,
|
48 |
+
"<|gu|>": 50333,
|
49 |
+
"<|haw|>": 50352,
|
50 |
+
"<|ha|>": 50354,
|
51 |
+
"<|he|>": 50279,
|
52 |
+
"<|hi|>": 50276,
|
53 |
+
"<|hr|>": 50291,
|
54 |
+
"<|ht|>": 50339,
|
55 |
+
"<|hu|>": 50286,
|
56 |
+
"<|hy|>": 50312,
|
57 |
+
"<|id|>": 50275,
|
58 |
+
"<|is|>": 50311,
|
59 |
+
"<|it|>": 50274,
|
60 |
+
"<|ja|>": 50266,
|
61 |
+
"<|jw|>": 50356,
|
62 |
+
"<|ka|>": 50329,
|
63 |
+
"<|kk|>": 50316,
|
64 |
+
"<|km|>": 50323,
|
65 |
+
"<|kn|>": 50306,
|
66 |
+
"<|ko|>": 50264,
|
67 |
+
"<|la|>": 50294,
|
68 |
+
"<|lb|>": 50345,
|
69 |
+
"<|ln|>": 50353,
|
70 |
+
"<|lo|>": 50336,
|
71 |
+
"<|lt|>": 50293,
|
72 |
+
"<|lv|>": 50301,
|
73 |
+
"<|mg|>": 50349,
|
74 |
+
"<|mi|>": 50295,
|
75 |
+
"<|mk|>": 50308,
|
76 |
+
"<|ml|>": 50296,
|
77 |
+
"<|mn|>": 50314,
|
78 |
+
"<|mr|>": 50320,
|
79 |
+
"<|ms|>": 50282,
|
80 |
+
"<|mt|>": 50343,
|
81 |
+
"<|my|>": 50346,
|
82 |
+
"<|ne|>": 50313,
|
83 |
+
"<|nl|>": 50271,
|
84 |
+
"<|nn|>": 50342,
|
85 |
+
"<|no|>": 50288,
|
86 |
+
"<|oc|>": 50328,
|
87 |
+
"<|pa|>": 50321,
|
88 |
+
"<|pl|>": 50269,
|
89 |
+
"<|ps|>": 50340,
|
90 |
+
"<|pt|>": 50267,
|
91 |
+
"<|ro|>": 50284,
|
92 |
+
"<|ru|>": 50263,
|
93 |
+
"<|sa|>": 50344,
|
94 |
+
"<|sd|>": 50332,
|
95 |
+
"<|si|>": 50322,
|
96 |
+
"<|sk|>": 50298,
|
97 |
+
"<|sl|>": 50305,
|
98 |
+
"<|sn|>": 50324,
|
99 |
+
"<|so|>": 50326,
|
100 |
+
"<|sq|>": 50317,
|
101 |
+
"<|sr|>": 50303,
|
102 |
+
"<|su|>": 50357,
|
103 |
+
"<|sv|>": 50273,
|
104 |
+
"<|sw|>": 50318,
|
105 |
+
"<|ta|>": 50287,
|
106 |
+
"<|te|>": 50299,
|
107 |
+
"<|tg|>": 50331,
|
108 |
+
"<|th|>": 50289,
|
109 |
+
"<|tk|>": 50341,
|
110 |
+
"<|tl|>": 50348,
|
111 |
+
"<|tr|>": 50268,
|
112 |
+
"<|tt|>": 50351,
|
113 |
+
"<|uk|>": 50280,
|
114 |
+
"<|ur|>": 50290,
|
115 |
+
"<|uz|>": 50337,
|
116 |
+
"<|vi|>": 50278,
|
117 |
+
"<|yi|>": 50335,
|
118 |
+
"<|yo|>": 50325,
|
119 |
+
"<|zh|>": 50260
|
120 |
+
},
|
121 |
+
"max_initial_timestamp_index": 1,
|
122 |
+
"max_length": 448,
|
123 |
+
"no_timestamps_token_id": 50363,
|
124 |
+
"pad_token_id": 50256,
|
125 |
+
"return_timestamps": false,
|
126 |
+
"suppress_tokens": [
|
127 |
+
1,
|
128 |
+
2,
|
129 |
+
7,
|
130 |
+
8,
|
131 |
+
9,
|
132 |
+
10,
|
133 |
+
14,
|
134 |
+
25,
|
135 |
+
26,
|
136 |
+
27,
|
137 |
+
28,
|
138 |
+
29,
|
139 |
+
31,
|
140 |
+
58,
|
141 |
+
59,
|
142 |
+
60,
|
143 |
+
61,
|
144 |
+
62,
|
145 |
+
63,
|
146 |
+
90,
|
147 |
+
91,
|
148 |
+
92,
|
149 |
+
93,
|
150 |
+
359,
|
151 |
+
503,
|
152 |
+
522,
|
153 |
+
542,
|
154 |
+
873,
|
155 |
+
893,
|
156 |
+
902,
|
157 |
+
918,
|
158 |
+
922,
|
159 |
+
931,
|
160 |
+
1350,
|
161 |
+
1853,
|
162 |
+
1982,
|
163 |
+
2460,
|
164 |
+
2627,
|
165 |
+
3246,
|
166 |
+
3253,
|
167 |
+
3268,
|
168 |
+
3536,
|
169 |
+
3846,
|
170 |
+
3961,
|
171 |
+
4183,
|
172 |
+
4667,
|
173 |
+
6585,
|
174 |
+
6647,
|
175 |
+
7273,
|
176 |
+
9061,
|
177 |
+
9383,
|
178 |
+
10428,
|
179 |
+
10929,
|
180 |
+
11938,
|
181 |
+
12033,
|
182 |
+
12331,
|
183 |
+
12562,
|
184 |
+
13793,
|
185 |
+
14157,
|
186 |
+
14635,
|
187 |
+
15265,
|
188 |
+
15618,
|
189 |
+
16553,
|
190 |
+
16604,
|
191 |
+
18362,
|
192 |
+
18956,
|
193 |
+
20075,
|
194 |
+
21675,
|
195 |
+
22520,
|
196 |
+
26130,
|
197 |
+
26161,
|
198 |
+
26435,
|
199 |
+
28279,
|
200 |
+
29464,
|
201 |
+
31650,
|
202 |
+
32302,
|
203 |
+
32470,
|
204 |
+
36865,
|
205 |
+
42863,
|
206 |
+
47425,
|
207 |
+
49870,
|
208 |
+
50254,
|
209 |
+
50258,
|
210 |
+
50360,
|
211 |
+
50361,
|
212 |
+
50362
|
213 |
+
],
|
214 |
+
"task_to_id": {
|
215 |
+
"transcribe": 50359,
|
216 |
+
"translate": 50358
|
217 |
+
},
|
218 |
+
"transformers_version": "4.27.0.dev0"
|
219 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d749e5631e265d18210664eb98fce618b396026f0a061f469bc743214b45da4
|
3 |
+
size 151253984
|