Commit
•
3cea572
1
Parent(s):
e9bcf70
update model card README.md
Browse files
README.md
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
---
|
2 |
-
language:
|
|
|
|
|
3 |
tags:
|
4 |
-
- whisper-medium
|
5 |
-
- mozilla-foundation/common_voice_11_0
|
6 |
-
- spanish
|
7 |
- whisper-event
|
|
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
10 |
-
metrics:
|
11 |
-
|
12 |
model-index:
|
13 |
-
- name: Whisper Medium
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
@@ -18,13 +18,62 @@ model-index:
|
|
18 |
dataset:
|
19 |
name: Common Voice 11.0
|
20 |
type: mozilla-foundation/common_voice_11_0
|
|
|
|
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value:
|
25 |
---
|
26 |
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
-
|
30 |
-
|
|
|
|
|
|
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 Medium Es - Juan Carlos Pi\xF1eros"
|
14 |
results:
|
15 |
- task:
|
16 |
name: 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: 5.563422365412595
|
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 Medium Es - Juan Carlos Piñeros
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.1679
|
38 |
+
- Wer: 5.5634
|
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: 32
|
59 |
+
- eval_batch_size: 16
|
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: 1000
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
+
| 0.0721 | 1.0 | 1000 | 0.1679 | 5.5634 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
|
76 |
+
- Transformers 4.26.0.dev0
|
77 |
+
- Pytorch 1.12.1+cu113
|
78 |
+
- Datasets 2.7.1.dev0
|
79 |
+
- Tokenizers 0.13.2
|