update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 Large Es - Javier Alonso
|
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: es
|
22 |
+
split: test
|
23 |
+
args: es
|
24 |
+
metrics:
|
25 |
+
- name: Wer
|
26 |
+
type: wer
|
27 |
+
value: 5.520113299724547
|
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 Large Es - Javier Alonso
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the Common Voice 11.0 dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.1571
|
38 |
+
- Wer: 5.5201
|
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: 8
|
59 |
+
- eval_batch_size: 2
|
60 |
+
- seed: 42
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_steps: 500
|
64 |
+
- training_steps: 10000
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
71 |
+
| 0.211 | 0.1 | 1000 | 0.2293 | 8.3896 |
|
72 |
+
| 0.2227 | 0.2 | 2000 | 0.2215 | 8.2552 |
|
73 |
+
| 0.1496 | 0.3 | 3000 | 0.2121 | 8.0362 |
|
74 |
+
| 0.1851 | 0.4 | 4000 | 0.2018 | 7.5197 |
|
75 |
+
| 0.1917 | 0.5 | 5000 | 0.1916 | 7.1098 |
|
76 |
+
| 0.1857 | 0.6 | 6000 | 0.1817 | 6.5537 |
|
77 |
+
| 0.1294 | 0.7 | 7000 | 0.1752 | 6.4062 |
|
78 |
+
| 0.1358 | 0.8 | 8000 | 0.1670 | 5.9950 |
|
79 |
+
| 0.1542 | 0.9 | 9000 | 0.1604 | 5.7858 |
|
80 |
+
| 0.1554 | 1.0 | 10000 | 0.1571 | 5.5201 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.26.0.dev0
|
86 |
+
- Pytorch 1.10.0+cu111
|
87 |
+
- Datasets 2.8.1.dev0
|
88 |
+
- Tokenizers 0.13.2
|