Commit
•
217bca6
1
Parent(s):
373973a
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- es
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- whisper-event
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_11_0
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: Whisper Small Vi - Shiv Kumar Ganesh
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: Common Voice 11.0
|
20 |
+
type: mozilla-foundation/common_voice_11_0
|
21 |
+
config: vi
|
22 |
+
split: test
|
23 |
+
args: vi
|
24 |
+
metrics:
|
25 |
+
- name: Wer
|
26 |
+
type: wer
|
27 |
+
value: 46.676902829567894
|
28 |
+
---
|
29 |
+
|
30 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
31 |
+
should probably proofread and complete it, then remove this comment. -->
|
32 |
+
|
33 |
+
# Whisper Small Vi - Shiv Kumar Ganesh
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.7220
|
38 |
+
- Wer: 46.6769
|
39 |
+
|
40 |
+
## Model description
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Intended uses & limitations
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training and evaluation data
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Training procedure
|
53 |
+
|
54 |
+
### Training hyperparameters
|
55 |
+
|
56 |
+
The following hyperparameters were used during training:
|
57 |
+
- learning_rate: 1e-05
|
58 |
+
- train_batch_size: 16
|
59 |
+
- eval_batch_size: 8
|
60 |
+
- seed: 42
|
61 |
+
- gradient_accumulation_steps: 2
|
62 |
+
- total_train_batch_size: 32
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- lr_scheduler_warmup_steps: 500
|
66 |
+
- training_steps: 1200
|
67 |
+
- mixed_precision_training: Native AMP
|
68 |
+
|
69 |
+
### Training results
|
70 |
+
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
72 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
73 |
+
| 1.7433 | 1.02 | 100 | 1.6824 | 155.0559 |
|
74 |
+
| 0.5929 | 2.04 | 200 | 0.8475 | 55.5824 |
|
75 |
+
| 0.1188 | 3.05 | 300 | 0.6646 | 47.2801 |
|
76 |
+
| 0.0672 | 5.0 | 400 | 0.7099 | 61.3292 |
|
77 |
+
| 0.0317 | 6.02 | 500 | 0.6951 | 49.9013 |
|
78 |
+
| 0.0169 | 7.04 | 600 | 0.7658 | 62.8866 |
|
79 |
+
| 0.0089 | 8.06 | 700 | 0.6681 | 34.2509 |
|
80 |
+
| 0.004 | 10.01 | 800 | 0.6875 | 43.8364 |
|
81 |
+
| 0.0015 | 11.03 | 900 | 0.7129 | 46.8195 |
|
82 |
+
| 0.0011 | 12.04 | 1000 | 0.7194 | 47.4775 |
|
83 |
+
| 0.0011 | 13.06 | 1100 | 0.7217 | 46.1505 |
|
84 |
+
| 0.001 | 15.01 | 1200 | 0.7220 | 46.6769 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.26.0.dev0
|
90 |
+
- Pytorch 1.13.0+cu116
|
91 |
+
- Datasets 2.8.1.dev0
|
92 |
+
- Tokenizers 0.13.2
|