End of training
Browse files- README.md +118 -0
- adapter.vie.safetensors +3 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
license: cc-by-nc-4.0
|
5 |
+
base_model: facebook/mms-1b-all
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- ducha07/audio_HTV_thoisu
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: ASR4-for-40-epochs
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: HTV news
|
20 |
+
type: ducha07/audio_HTV_thoisu
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.26843348202571504
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# ASR4-for-40-epochs
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the HTV news dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.4791
|
35 |
+
- Wer: 0.2684
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.001
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- lr_scheduler_warmup_steps: 100
|
61 |
+
- num_epochs: 40
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 5.1111 | 0.92 | 100 | 0.7687 | 0.4387 |
|
69 |
+
| 1.1201 | 1.83 | 200 | 0.6388 | 0.3767 |
|
70 |
+
| 0.9734 | 2.75 | 300 | 0.6319 | 0.3658 |
|
71 |
+
| 0.9297 | 3.67 | 400 | 0.5740 | 0.3373 |
|
72 |
+
| 0.9142 | 4.59 | 500 | 0.5591 | 0.3268 |
|
73 |
+
| 0.8462 | 5.5 | 600 | 0.5627 | 0.3227 |
|
74 |
+
| 0.8366 | 6.42 | 700 | 0.5491 | 0.3158 |
|
75 |
+
| 0.8272 | 7.34 | 800 | 0.5398 | 0.3243 |
|
76 |
+
| 0.8137 | 8.26 | 900 | 0.5363 | 0.3113 |
|
77 |
+
| 0.7643 | 9.17 | 1000 | 0.5528 | 0.3117 |
|
78 |
+
| 0.7738 | 10.09 | 1100 | 0.5194 | 0.3285 |
|
79 |
+
| 0.7622 | 11.01 | 1200 | 0.5348 | 0.3043 |
|
80 |
+
| 0.707 | 11.93 | 1300 | 0.5179 | 0.2909 |
|
81 |
+
| 0.7242 | 12.84 | 1400 | 0.5153 | 0.3138 |
|
82 |
+
| 0.7093 | 13.76 | 1500 | 0.5116 | 0.2951 |
|
83 |
+
| 0.673 | 14.68 | 1600 | 0.5002 | 0.2941 |
|
84 |
+
| 0.6877 | 15.6 | 1700 | 0.4958 | 0.3050 |
|
85 |
+
| 0.6665 | 16.51 | 1800 | 0.5032 | 0.2865 |
|
86 |
+
| 0.6507 | 17.43 | 1900 | 0.4871 | 0.2809 |
|
87 |
+
| 0.6308 | 18.35 | 2000 | 0.4953 | 0.2947 |
|
88 |
+
| 0.6507 | 19.27 | 2100 | 0.4998 | 0.2837 |
|
89 |
+
| 0.6027 | 20.18 | 2200 | 0.4963 | 0.2868 |
|
90 |
+
| 0.623 | 21.1 | 2300 | 0.4955 | 0.2953 |
|
91 |
+
| 0.6047 | 22.02 | 2400 | 0.5034 | 0.2852 |
|
92 |
+
| 0.5825 | 22.94 | 2500 | 0.4781 | 0.2795 |
|
93 |
+
| 0.585 | 23.85 | 2600 | 0.4851 | 0.2843 |
|
94 |
+
| 0.5838 | 24.77 | 2700 | 0.4957 | 0.2742 |
|
95 |
+
| 0.5718 | 25.69 | 2800 | 0.4885 | 0.2810 |
|
96 |
+
| 0.5646 | 26.61 | 2900 | 0.4778 | 0.2724 |
|
97 |
+
| 0.5476 | 27.52 | 3000 | 0.4914 | 0.2751 |
|
98 |
+
| 0.5333 | 28.44 | 3100 | 0.4879 | 0.2788 |
|
99 |
+
| 0.5533 | 29.36 | 3200 | 0.4820 | 0.2726 |
|
100 |
+
| 0.5321 | 30.28 | 3300 | 0.4816 | 0.2686 |
|
101 |
+
| 0.5161 | 31.19 | 3400 | 0.4865 | 0.2812 |
|
102 |
+
| 0.5326 | 32.11 | 3500 | 0.4818 | 0.2704 |
|
103 |
+
| 0.5188 | 33.03 | 3600 | 0.4816 | 0.2669 |
|
104 |
+
| 0.506 | 33.94 | 3700 | 0.4804 | 0.2755 |
|
105 |
+
| 0.5122 | 34.86 | 3800 | 0.4803 | 0.2667 |
|
106 |
+
| 0.506 | 35.78 | 3900 | 0.4785 | 0.2708 |
|
107 |
+
| 0.5064 | 36.7 | 4000 | 0.4755 | 0.2730 |
|
108 |
+
| 0.4997 | 37.61 | 4100 | 0.4804 | 0.2708 |
|
109 |
+
| 0.4904 | 38.53 | 4200 | 0.4772 | 0.2678 |
|
110 |
+
| 0.4774 | 39.45 | 4300 | 0.4791 | 0.2684 |
|
111 |
+
|
112 |
+
|
113 |
+
### Framework versions
|
114 |
+
|
115 |
+
- Transformers 4.37.0.dev0
|
116 |
+
- Pytorch 2.1.0+cu121
|
117 |
+
- Datasets 2.16.1
|
118 |
+
- Tokenizers 0.15.0
|
adapter.vie.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb3a0027bcb542423b9af6c0701078a0034648df2eb41207a86345a58b955dee
|
3 |
+
size 9203360
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3859295720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c15a3fc3ecb9853b3a4b2b00765b12c437d6fefeed96d7dbaffe3015830df0
|
3 |
size 3859295720
|