bigmorning
commited on
Commit
•
1eb8b3d
1
Parent(s):
4a2103d
Upload TFWhisperForConditionalGeneration
Browse files- README.md +64 -0
- config.json +144 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: whisper3_0010
|
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 |
+
# whisper3_0010
|
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: 0.7159
|
18 |
+
- Train Accuracy: 0.0297
|
19 |
+
- Validation Loss: 0.7918
|
20 |
+
- Validation Accuracy: 0.0300
|
21 |
+
- Epoch: 9
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- 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}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
46 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
47 |
+
| 5.0832 | 0.0116 | 4.4298 | 0.0124 | 0 |
|
48 |
+
| 4.3130 | 0.0131 | 4.0733 | 0.0141 | 1 |
|
49 |
+
| 3.9211 | 0.0146 | 3.6762 | 0.0157 | 2 |
|
50 |
+
| 3.5505 | 0.0159 | 3.3453 | 0.0171 | 3 |
|
51 |
+
| 3.1592 | 0.0175 | 2.8062 | 0.0199 | 4 |
|
52 |
+
| 2.2581 | 0.0220 | 1.7622 | 0.0252 | 5 |
|
53 |
+
| 1.4671 | 0.0259 | 1.2711 | 0.0276 | 6 |
|
54 |
+
| 1.0779 | 0.0278 | 1.0220 | 0.0288 | 7 |
|
55 |
+
| 0.8591 | 0.0290 | 0.8836 | 0.0295 | 8 |
|
56 |
+
| 0.7159 | 0.0297 | 0.7918 | 0.0300 | 9 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.25.0.dev0
|
62 |
+
- TensorFlow 2.9.2
|
63 |
+
- Datasets 2.6.1
|
64 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
50259
|
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 |
+
1,
|
52 |
+
2,
|
53 |
+
6,
|
54 |
+
7,
|
55 |
+
8,
|
56 |
+
9,
|
57 |
+
10,
|
58 |
+
12,
|
59 |
+
14,
|
60 |
+
25,
|
61 |
+
26,
|
62 |
+
27,
|
63 |
+
28,
|
64 |
+
29,
|
65 |
+
31,
|
66 |
+
58,
|
67 |
+
59,
|
68 |
+
60,
|
69 |
+
61,
|
70 |
+
62,
|
71 |
+
63,
|
72 |
+
90,
|
73 |
+
91,
|
74 |
+
92,
|
75 |
+
93,
|
76 |
+
359,
|
77 |
+
503,
|
78 |
+
522,
|
79 |
+
542,
|
80 |
+
873,
|
81 |
+
893,
|
82 |
+
902,
|
83 |
+
918,
|
84 |
+
922,
|
85 |
+
931,
|
86 |
+
1350,
|
87 |
+
1853,
|
88 |
+
1982,
|
89 |
+
2460,
|
90 |
+
2627,
|
91 |
+
3246,
|
92 |
+
3253,
|
93 |
+
3268,
|
94 |
+
3536,
|
95 |
+
3846,
|
96 |
+
3961,
|
97 |
+
4183,
|
98 |
+
4667,
|
99 |
+
6585,
|
100 |
+
6647,
|
101 |
+
7273,
|
102 |
+
9061,
|
103 |
+
9383,
|
104 |
+
10428,
|
105 |
+
10929,
|
106 |
+
11938,
|
107 |
+
12033,
|
108 |
+
12331,
|
109 |
+
12562,
|
110 |
+
13793,
|
111 |
+
14157,
|
112 |
+
14635,
|
113 |
+
15265,
|
114 |
+
15618,
|
115 |
+
16553,
|
116 |
+
16604,
|
117 |
+
18362,
|
118 |
+
18956,
|
119 |
+
20075,
|
120 |
+
21675,
|
121 |
+
22520,
|
122 |
+
26130,
|
123 |
+
26161,
|
124 |
+
26435,
|
125 |
+
28279,
|
126 |
+
29464,
|
127 |
+
31650,
|
128 |
+
32302,
|
129 |
+
32470,
|
130 |
+
36865,
|
131 |
+
42863,
|
132 |
+
47425,
|
133 |
+
49870,
|
134 |
+
50254,
|
135 |
+
50258,
|
136 |
+
50360,
|
137 |
+
50361,
|
138 |
+
50362
|
139 |
+
],
|
140 |
+
"torch_dtype": "float32",
|
141 |
+
"transformers_version": "4.25.0.dev0",
|
142 |
+
"use_cache": true,
|
143 |
+
"vocab_size": 51865
|
144 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb6ac93132b1d7438d4ef32e10e176a24c4e0e027bb787495eed24fb260c296
|
3 |
+
size 151253984
|