update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- audiofolder
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: whisper-medium-ar-original
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: audiofolder
|
17 |
+
type: audiofolder
|
18 |
+
config: default
|
19 |
+
split: train
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 14.108618654073199
|
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 |
+
# whisper-medium-ar-original
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the audiofolder dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.1852
|
35 |
+
- Wer: 14.1086
|
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: 1e-05
|
55 |
+
- train_batch_size: 24
|
56 |
+
- eval_batch_size: 24
|
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: 500
|
61 |
+
- training_steps: 8000
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
68 |
+
| 0.115 | 1.01 | 400 | 0.1204 | 18.6541 |
|
69 |
+
| 0.0774 | 2.02 | 800 | 0.1074 | 15.5844 |
|
70 |
+
| 0.0438 | 3.03 | 1200 | 0.1160 | 16.4699 |
|
71 |
+
| 0.0233 | 4.04 | 1600 | 0.1279 | 15.1122 |
|
72 |
+
| 0.0131 | 5.05 | 2000 | 0.1350 | 15.5254 |
|
73 |
+
| 0.0051 | 6.06 | 2400 | 0.1455 | 14.9941 |
|
74 |
+
| 0.0035 | 7.07 | 2800 | 0.1464 | 14.1677 |
|
75 |
+
| 0.0032 | 8.08 | 3200 | 0.1545 | 14.8170 |
|
76 |
+
| 0.0013 | 9.09 | 3600 | 0.1623 | 13.8725 |
|
77 |
+
| 0.0013 | 10.1 | 4000 | 0.1543 | 13.4002 |
|
78 |
+
| 0.0006 | 11.11 | 4400 | 0.1653 | 14.1677 |
|
79 |
+
| 0.0006 | 12.12 | 4800 | 0.1699 | 13.7544 |
|
80 |
+
| 0.0003 | 13.13 | 5200 | 0.1705 | 13.4593 |
|
81 |
+
| 0.0001 | 14.14 | 5600 | 0.1733 | 13.6954 |
|
82 |
+
| 0.0002 | 15.15 | 6000 | 0.1768 | 13.8725 |
|
83 |
+
| 0.0001 | 16.16 | 6400 | 0.1786 | 13.7544 |
|
84 |
+
| 0.0 | 17.17 | 6800 | 0.1826 | 13.9906 |
|
85 |
+
| 0.0 | 18.18 | 7200 | 0.1839 | 14.0496 |
|
86 |
+
| 0.0 | 19.19 | 7600 | 0.1848 | 14.0496 |
|
87 |
+
| 0.0 | 20.2 | 8000 | 0.1852 | 14.1086 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.25.1
|
93 |
+
- Pytorch 1.12.1
|
94 |
+
- Datasets 2.8.0
|
95 |
+
- Tokenizers 0.13.2
|