Hugging Face's logo

bigmorning
/
whisper_end22

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
bigmorning commited on
Commit
6328444
•
1 Parent(s): d4e53fa

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (3) hide show
  1. README.md +76 -0
  2. config.json +42 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: whisper_end22
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_end22
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: 0.1061
18
+ - Train Accuracy: 0.0341
19
+ - Validation Loss: 0.5635
20
+ - Validation Accuracy: 0.0314
21
+ - Epoch: 22
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
+ | 5.0856 | 0.0116 | 4.4440 | 0.0123 | 0 |
48
+ | 4.3149 | 0.0131 | 4.0521 | 0.0142 | 1 |
49
+ | 3.9260 | 0.0146 | 3.7264 | 0.0153 | 2 |
50
+ | 3.5418 | 0.0160 | 3.3026 | 0.0174 | 3 |
51
+ | 2.7510 | 0.0198 | 2.0157 | 0.0241 | 4 |
52
+ | 1.6782 | 0.0250 | 1.3567 | 0.0273 | 5 |
53
+ | 1.1705 | 0.0274 | 1.0678 | 0.0286 | 6 |
54
+ | 0.9126 | 0.0287 | 0.9152 | 0.0294 | 7 |
55
+ | 0.7514 | 0.0296 | 0.8057 | 0.0299 | 8 |
56
+ | 0.6371 | 0.0302 | 0.7409 | 0.0302 | 9 |
57
+ | 0.5498 | 0.0307 | 0.6854 | 0.0306 | 10 |
58
+ | 0.4804 | 0.0312 | 0.6518 | 0.0307 | 11 |
59
+ | 0.4214 | 0.0316 | 0.6200 | 0.0310 | 12 |
60
+ | 0.3713 | 0.0319 | 0.5947 | 0.0311 | 13 |
61
+ | 0.3281 | 0.0322 | 0.5841 | 0.0311 | 14 |
62
+ | 0.2891 | 0.0325 | 0.5700 | 0.0313 | 15 |
63
+ | 0.2550 | 0.0328 | 0.5614 | 0.0313 | 16 |
64
+ | 0.2237 | 0.0331 | 0.5572 | 0.0313 | 17 |
65
+ | 0.1959 | 0.0333 | 0.5563 | 0.0314 | 18 |
66
+ | 0.1698 | 0.0335 | 0.5530 | 0.0314 | 19 |
67
+ | 0.1455 | 0.0337 | 0.5590 | 0.0314 | 20 |
68
+ | 0.1242 | 0.0339 | 0.5743 | 0.0313 | 21 |
69
+ | 0.1061 | 0.0341 | 0.5635 | 0.0314 | 22 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.25.0.dev0
75
+ - TensorFlow 2.9.2
76
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 4,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "suppress_tokens": [],
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.25.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b22fecf86d65722d362fc89585e02b215f0ea597e9150c7c74a96ce7df9a8f9
3
+ size 151253984