Model save
Browse files- README.md +83 -0
- generation_config.json +13 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: xmzhu/whisper-tiny-zh
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice_16_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: xmzhu/whisper-tiny-zh
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice_16_0
|
18 |
+
type: common_voice_16_0
|
19 |
+
config: zh-CN
|
20 |
+
split: test
|
21 |
+
args: zh-CN
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 91.15267507612005
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# xmzhu/whisper-tiny-zh
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [xmzhu/whisper-tiny-zh](https://huggingface.co/xmzhu/whisper-tiny-zh) on the common_voice_16_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.5744
|
36 |
+
- Wer: 91.1527
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-07
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 64
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_steps: 200
|
64 |
+
- training_steps: 1000
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
71 |
+
| 0.6689 | 0.2 | 200 | 0.5854 | 91.6311 |
|
72 |
+
| 0.6314 | 1.07 | 400 | 0.5791 | 91.1788 |
|
73 |
+
| 0.653 | 1.27 | 600 | 0.5759 | 91.1266 |
|
74 |
+
| 0.699 | 2.13 | 800 | 0.5749 | 91.2049 |
|
75 |
+
| 0.5613 | 3.0 | 1000 | 0.5744 | 91.1527 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.37.0.dev0
|
81 |
+
- Pytorch 2.1.2+cu121
|
82 |
+
- Datasets 2.16.2.dev0
|
83 |
+
- Tokenizers 0.15.0
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_suppress_tokens": [
|
3 |
+
220,
|
4 |
+
50257
|
5 |
+
],
|
6 |
+
"bos_token_id": 50257,
|
7 |
+
"decoder_start_token_id": 50258,
|
8 |
+
"eos_token_id": 50257,
|
9 |
+
"max_length": 448,
|
10 |
+
"pad_token_id": 50257,
|
11 |
+
"transformers_version": "4.37.0.dev0",
|
12 |
+
"use_cache": false
|
13 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47f2500db40e98322da6eb19901c6c00473a61b3836b7fcdebb5725c85f3a84e
|
3 |
size 151061672
|