Model save
Browse files
README.md
CHANGED
|
@@ -1,3 +1,70 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: whisper_CN
|
| 10 |
+
results: []
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# whisper_CN
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2598
|
| 21 |
+
- Wer: 266.9357
|
| 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 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 200
|
| 49 |
+
- training_steps: 10000
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 0.0378 | 2.84 | 2000 | 0.1870 | 195.0945 |
|
| 57 |
+
| 0.0023 | 5.67 | 4000 | 0.2071 | 240.6880 |
|
| 58 |
+
| 0.0006 | 8.51 | 6000 | 0.2149 | 160.2463 |
|
| 59 |
+
| 0.0003 | 11.35 | 8000 | 0.2226 | 164.5148 |
|
| 60 |
+
| 0.0002 | 28.4 | 10000 | 0.2332 | 160.5649 |
|
| 61 |
+
| 0.0002 | 34.08 | 12000 | 0.2460 | 301.9112 |
|
| 62 |
+
| 0.0001 | 39.76 | 14000 | 0.2598 | 266.9357 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.35.2
|
| 68 |
+
- Pytorch 2.1.1+cu121
|
| 69 |
+
- Datasets 2.15.0
|
| 70 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
|
@@ -25,20 +25,7 @@
|
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 12,
|
| 27 |
"eos_token_id": 50257,
|
| 28 |
-
"forced_decoder_ids":
|
| 29 |
-
[
|
| 30 |
-
1,
|
| 31 |
-
50259
|
| 32 |
-
],
|
| 33 |
-
[
|
| 34 |
-
2,
|
| 35 |
-
50359
|
| 36 |
-
],
|
| 37 |
-
[
|
| 38 |
-
3,
|
| 39 |
-
50363
|
| 40 |
-
]
|
| 41 |
-
],
|
| 42 |
"init_std": 0.02,
|
| 43 |
"is_encoder_decoder": true,
|
| 44 |
"mask_feature_length": 10,
|
|
@@ -56,94 +43,7 @@
|
|
| 56 |
"num_mel_bins": 80,
|
| 57 |
"pad_token_id": 50257,
|
| 58 |
"scale_embedding": false,
|
| 59 |
-
"suppress_tokens": [
|
| 60 |
-
1,
|
| 61 |
-
2,
|
| 62 |
-
7,
|
| 63 |
-
8,
|
| 64 |
-
9,
|
| 65 |
-
10,
|
| 66 |
-
14,
|
| 67 |
-
25,
|
| 68 |
-
26,
|
| 69 |
-
27,
|
| 70 |
-
28,
|
| 71 |
-
29,
|
| 72 |
-
31,
|
| 73 |
-
58,
|
| 74 |
-
59,
|
| 75 |
-
60,
|
| 76 |
-
61,
|
| 77 |
-
62,
|
| 78 |
-
63,
|
| 79 |
-
90,
|
| 80 |
-
91,
|
| 81 |
-
92,
|
| 82 |
-
93,
|
| 83 |
-
359,
|
| 84 |
-
503,
|
| 85 |
-
522,
|
| 86 |
-
542,
|
| 87 |
-
873,
|
| 88 |
-
893,
|
| 89 |
-
902,
|
| 90 |
-
918,
|
| 91 |
-
922,
|
| 92 |
-
931,
|
| 93 |
-
1350,
|
| 94 |
-
1853,
|
| 95 |
-
1982,
|
| 96 |
-
2460,
|
| 97 |
-
2627,
|
| 98 |
-
3246,
|
| 99 |
-
3253,
|
| 100 |
-
3268,
|
| 101 |
-
3536,
|
| 102 |
-
3846,
|
| 103 |
-
3961,
|
| 104 |
-
4183,
|
| 105 |
-
4667,
|
| 106 |
-
6585,
|
| 107 |
-
6647,
|
| 108 |
-
7273,
|
| 109 |
-
9061,
|
| 110 |
-
9383,
|
| 111 |
-
10428,
|
| 112 |
-
10929,
|
| 113 |
-
11938,
|
| 114 |
-
12033,
|
| 115 |
-
12331,
|
| 116 |
-
12562,
|
| 117 |
-
13793,
|
| 118 |
-
14157,
|
| 119 |
-
14635,
|
| 120 |
-
15265,
|
| 121 |
-
15618,
|
| 122 |
-
16553,
|
| 123 |
-
16604,
|
| 124 |
-
18362,
|
| 125 |
-
18956,
|
| 126 |
-
20075,
|
| 127 |
-
21675,
|
| 128 |
-
22520,
|
| 129 |
-
26130,
|
| 130 |
-
26161,
|
| 131 |
-
26435,
|
| 132 |
-
28279,
|
| 133 |
-
29464,
|
| 134 |
-
31650,
|
| 135 |
-
32302,
|
| 136 |
-
32470,
|
| 137 |
-
36865,
|
| 138 |
-
42863,
|
| 139 |
-
47425,
|
| 140 |
-
49870,
|
| 141 |
-
50254,
|
| 142 |
-
50258,
|
| 143 |
-
50360,
|
| 144 |
-
50361,
|
| 145 |
-
50362
|
| 146 |
-
],
|
| 147 |
"torch_dtype": "float32",
|
| 148 |
"transformers_version": "4.35.2",
|
| 149 |
"use_cache": true,
|
|
|
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 12,
|
| 27 |
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"init_std": 0.02,
|
| 30 |
"is_encoder_decoder": true,
|
| 31 |
"mask_feature_length": 10,
|
|
|
|
| 43 |
"num_mel_bins": 80,
|
| 44 |
"pad_token_id": 50257,
|
| 45 |
"scale_embedding": false,
|
| 46 |
+
"suppress_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"torch_dtype": "float32",
|
| 48 |
"transformers_version": "4.35.2",
|
| 49 |
"use_cache": true,
|
runs/Dec08_15-11-23_smurf/events.out.tfevents.1702041112.smurf.1132654.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5219e277871a76884dabccd9291f61c5eaec31977c71453c319933238f57db42
|
| 3 |
+
size 38344
|
runs/Dec13_23-46-55_rename/events.out.tfevents.1702504073.rename.1355419.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc26d6fa99c0fe8c02446677336ecddc5f5f4588f4b3aa0736bce72268bd45ca
|
| 3 |
+
size 5371
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8870c453f84f85b1811d8a0ac8c2044c0629822abe75c7def9d3da0ff06e405d
|
| 3 |
size 4728
|