Commit
•
e9ab370
1
Parent(s):
fdb32d2
Upload TFWhisperForConditionalGeneration
Browse files- README.md +73 -0
- config.json +42 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: whisper_0020
|
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_0020
|
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: 0.1698
|
18 |
+
- Train Accuracy: 0.0335
|
19 |
+
- Validation Loss: 0.5530
|
20 |
+
- Validation Accuracy: 0.0314
|
21 |
+
- Epoch: 19
|
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 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.25.0.dev0
|
72 |
+
- TensorFlow 2.9.2
|
73 |
+
- 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:a6d1d4d232d641d37de329fc18b90a785876ac815850de37f29350ca72f8bb3a
|
3 |
+
size 151253984
|