bigmorning
commited on
Commit
•
043aaa1
1
Parent(s):
e672016
Upload TFWhisperForConditionalGeneration
Browse files- README.md +91 -0
- config.json +199 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: whisper_havest_0035
|
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_havest_0035
|
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: 3.5897
|
18 |
+
- Train Accuracy: 0.0150
|
19 |
+
- Train Do Wer: 1.0
|
20 |
+
- Validation Loss: 4.5822
|
21 |
+
- Validation Accuracy: 0.0130
|
22 |
+
- Validation Do Wer: 1.0
|
23 |
+
- Epoch: 34
|
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 Do Wer | Validation Loss | Validation Accuracy | Validation Do Wer | Epoch |
|
48 |
+
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
|
49 |
+
| 9.9191 | 0.0046 | 1.0 | 8.5836 | 0.0067 | 1.0 | 0 |
|
50 |
+
| 8.0709 | 0.0083 | 1.0 | 7.4667 | 0.0089 | 1.0 | 1 |
|
51 |
+
| 7.1652 | 0.0100 | 1.0 | 6.8204 | 0.0112 | 1.0 | 2 |
|
52 |
+
| 6.7196 | 0.0114 | 1.0 | 6.5192 | 0.0114 | 1.0 | 3 |
|
53 |
+
| 6.4115 | 0.0115 | 1.0 | 6.2357 | 0.0115 | 1.0 | 4 |
|
54 |
+
| 6.1085 | 0.0115 | 1.0 | 5.9657 | 0.0115 | 1.0 | 5 |
|
55 |
+
| 5.8206 | 0.0115 | 1.0 | 5.7162 | 0.0115 | 1.0 | 6 |
|
56 |
+
| 5.5567 | 0.0115 | 1.0 | 5.4963 | 0.0115 | 1.0 | 7 |
|
57 |
+
| 5.3223 | 0.0116 | 1.0 | 5.3096 | 0.0116 | 1.0 | 8 |
|
58 |
+
| 5.1222 | 0.0117 | 1.0 | 5.1600 | 0.0117 | 1.0 | 9 |
|
59 |
+
| 4.9580 | 0.0117 | 1.0 | 5.0391 | 0.0118 | 1.0 | 10 |
|
60 |
+
| 4.8251 | 0.0119 | 1.0 | 4.9427 | 0.0118 | 1.0 | 11 |
|
61 |
+
| 4.7171 | 0.0119 | 1.0 | 4.8691 | 0.0119 | 1.0 | 12 |
|
62 |
+
| 4.6284 | 0.0121 | 1.0 | 4.8123 | 0.0120 | 1.0 | 13 |
|
63 |
+
| 4.5508 | 0.0121 | 1.0 | 4.7620 | 0.0121 | 1.0 | 14 |
|
64 |
+
| 4.4855 | 0.0123 | 1.0 | 4.7260 | 0.0121 | 1.0 | 15 |
|
65 |
+
| 4.4305 | 0.0124 | 1.0 | 4.7018 | 0.0123 | 1.0 | 16 |
|
66 |
+
| 4.3788 | 0.0125 | 1.0 | 4.6738 | 0.0123 | 1.0 | 17 |
|
67 |
+
| 4.3305 | 0.0127 | 1.0 | 4.6525 | 0.0124 | 1.0 | 18 |
|
68 |
+
| 4.2860 | 0.0128 | 1.0 | 4.6401 | 0.0125 | 1.0 | 19 |
|
69 |
+
| 4.2451 | 0.0130 | 1.0 | 4.6234 | 0.0126 | 1.0 | 20 |
|
70 |
+
| 4.1994 | 0.0132 | 1.0 | 4.6077 | 0.0128 | 1.0 | 21 |
|
71 |
+
| 4.1521 | 0.0133 | 1.0 | 4.6098 | 0.0129 | 1.0 | 22 |
|
72 |
+
| 4.1148 | 0.0134 | 1.0 | 4.5919 | 0.0129 | 1.0 | 23 |
|
73 |
+
| 4.0701 | 0.0135 | 1.0 | 4.6038 | 0.0128 | 1.0 | 24 |
|
74 |
+
| 4.0199 | 0.0137 | 1.0 | 4.5777 | 0.0130 | 1.0 | 25 |
|
75 |
+
| 3.9631 | 0.0138 | 1.0 | 4.5734 | 0.0131 | 1.0 | 26 |
|
76 |
+
| 3.9175 | 0.0140 | 1.0 | 4.5866 | 0.0129 | 1.0 | 27 |
|
77 |
+
| 3.8690 | 0.0142 | 1.0 | 4.5900 | 0.0129 | 1.0 | 28 |
|
78 |
+
| 3.8276 | 0.0143 | 1.0 | 4.5602 | 0.0131 | 1.0 | 29 |
|
79 |
+
| 3.7499 | 0.0145 | 1.0 | 4.5619 | 0.0132 | 1.0 | 30 |
|
80 |
+
| 3.6968 | 0.0147 | 1.0 | 4.6203 | 0.0133 | 1.0 | 31 |
|
81 |
+
| 3.6714 | 0.0149 | 1.0 | 4.7075 | 0.0133 | 1.0 | 32 |
|
82 |
+
| 3.6318 | 0.0149 | 1.0 | 4.6638 | 0.0125 | 1.0 | 33 |
|
83 |
+
| 3.5897 | 0.0150 | 1.0 | 4.5822 | 0.0130 | 1.0 | 34 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.25.0.dev0
|
89 |
+
- TensorFlow 2.9.2
|
90 |
+
- Datasets 2.6.1
|
91 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-tiny",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"WhisperForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"begin_suppress_tokens": [
|
10 |
+
220,
|
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 |
+
"max_length": 448,
|
43 |
+
"max_source_positions": 1500,
|
44 |
+
"max_target_positions": 448,
|
45 |
+
"model_type": "whisper",
|
46 |
+
"num_hidden_layers": 4,
|
47 |
+
"num_mel_bins": 80,
|
48 |
+
"pad_token_id": 50257,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"suppress_tokens": [
|
51 |
+
0,
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
3,
|
55 |
+
4,
|
56 |
+
10968,
|
57 |
+
10969,
|
58 |
+
10970,
|
59 |
+
10971,
|
60 |
+
10972,
|
61 |
+
10973,
|
62 |
+
10974,
|
63 |
+
10975,
|
64 |
+
10976,
|
65 |
+
10977,
|
66 |
+
10978,
|
67 |
+
10979,
|
68 |
+
10980,
|
69 |
+
10981,
|
70 |
+
10982,
|
71 |
+
10983,
|
72 |
+
10984,
|
73 |
+
10985,
|
74 |
+
10986,
|
75 |
+
10987,
|
76 |
+
10988,
|
77 |
+
10989,
|
78 |
+
10990,
|
79 |
+
10991,
|
80 |
+
10992,
|
81 |
+
10993,
|
82 |
+
10994,
|
83 |
+
10995,
|
84 |
+
10996,
|
85 |
+
10997,
|
86 |
+
50256,
|
87 |
+
50257,
|
88 |
+
50258,
|
89 |
+
50259,
|
90 |
+
50260,
|
91 |
+
50261,
|
92 |
+
50262,
|
93 |
+
50263,
|
94 |
+
50264,
|
95 |
+
50265,
|
96 |
+
50266,
|
97 |
+
50267,
|
98 |
+
50268,
|
99 |
+
50269,
|
100 |
+
50270,
|
101 |
+
50271,
|
102 |
+
50272,
|
103 |
+
50273,
|
104 |
+
50274,
|
105 |
+
50275,
|
106 |
+
50276,
|
107 |
+
50277,
|
108 |
+
50278,
|
109 |
+
50279,
|
110 |
+
50280,
|
111 |
+
50281,
|
112 |
+
50282,
|
113 |
+
50283,
|
114 |
+
50284,
|
115 |
+
50285,
|
116 |
+
50286,
|
117 |
+
50287,
|
118 |
+
50288,
|
119 |
+
50289,
|
120 |
+
50290,
|
121 |
+
50291,
|
122 |
+
50292,
|
123 |
+
50293,
|
124 |
+
50294,
|
125 |
+
50295,
|
126 |
+
50296,
|
127 |
+
50297,
|
128 |
+
50298,
|
129 |
+
50299,
|
130 |
+
50300,
|
131 |
+
50301,
|
132 |
+
50302,
|
133 |
+
50303,
|
134 |
+
50304,
|
135 |
+
50305,
|
136 |
+
50306,
|
137 |
+
50307,
|
138 |
+
50308,
|
139 |
+
50309,
|
140 |
+
50310,
|
141 |
+
50311,
|
142 |
+
50312,
|
143 |
+
50313,
|
144 |
+
50314,
|
145 |
+
50315,
|
146 |
+
50316,
|
147 |
+
50317,
|
148 |
+
50318,
|
149 |
+
50319,
|
150 |
+
50320,
|
151 |
+
50321,
|
152 |
+
50322,
|
153 |
+
50323,
|
154 |
+
50324,
|
155 |
+
50325,
|
156 |
+
50326,
|
157 |
+
50327,
|
158 |
+
50328,
|
159 |
+
50329,
|
160 |
+
50330,
|
161 |
+
50331,
|
162 |
+
50332,
|
163 |
+
50333,
|
164 |
+
50334,
|
165 |
+
50335,
|
166 |
+
50336,
|
167 |
+
50337,
|
168 |
+
50338,
|
169 |
+
50339,
|
170 |
+
50340,
|
171 |
+
50341,
|
172 |
+
50342,
|
173 |
+
50343,
|
174 |
+
50344,
|
175 |
+
50345,
|
176 |
+
50346,
|
177 |
+
50347,
|
178 |
+
50348,
|
179 |
+
50349,
|
180 |
+
50350,
|
181 |
+
50351,
|
182 |
+
50352,
|
183 |
+
50353,
|
184 |
+
50354,
|
185 |
+
50355,
|
186 |
+
50356,
|
187 |
+
50357,
|
188 |
+
50358,
|
189 |
+
50359,
|
190 |
+
50360,
|
191 |
+
50361,
|
192 |
+
50362,
|
193 |
+
50363
|
194 |
+
],
|
195 |
+
"torch_dtype": "float32",
|
196 |
+
"transformers_version": "4.25.0.dev0",
|
197 |
+
"use_cache": true,
|
198 |
+
"vocab_size": 51865
|
199 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2987a94e396c7148908b17a0675182e051d7faee8d9d9802357be4930a6a33ce
|
3 |
+
size 151253984
|