marinone94
commited on
Commit
•
22780cf
1
Parent(s):
8ac322f
update model card README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ datasets:
|
|
7 |
metrics:
|
8 |
- wer
|
9 |
model-index:
|
10 |
-
- name:
|
11 |
results:
|
12 |
- task:
|
13 |
name: Automatic Speech Recognition
|
@@ -21,18 +21,18 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value:
|
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 |
-
#
|
31 |
|
32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 1.
|
35 |
-
- Wer:
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -51,35 +51,27 @@ More information needed
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
-
- learning_rate:
|
55 |
-
- train_batch_size:
|
56 |
-
- eval_batch_size:
|
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_ratio: 0.
|
61 |
-
- training_steps:
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.1161 | 0.29 | 33 | 1.1921 | 200.2395 |
|
71 |
-
| 0.9216 | 1.05 | 44 | 1.1263 | 186.5240 |
|
72 |
-
| 0.8441 | 1.15 | 55 | 1.0946 | 179.3230 |
|
73 |
-
| 0.8505 | 1.25 | 66 | 1.0748 | 159.6839 |
|
74 |
-
| 0.7844 | 2.01 | 77 | 1.0585 | 163.2924 |
|
75 |
-
| 0.7208 | 2.11 | 88 | 1.0491 | 158.1031 |
|
76 |
-
| 0.6481 | 2.21 | 99 | 1.0468 | 158.5183 |
|
77 |
-
| 0.7912 | 2.3 | 110 | 1.0456 | 168.6093 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
-
- Transformers 4.
|
83 |
-
- Pytorch 1.13.1+
|
84 |
-
- Datasets 2.
|
85 |
- Tokenizers 0.13.2
|
|
|
7 |
metrics:
|
8 |
- wer
|
9 |
model-index:
|
10 |
+
- name: whisper-training-blog
|
11 |
results:
|
12 |
- task:
|
13 |
name: Automatic Speech Recognition
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 123.40425531914893
|
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-training-blog
|
31 |
|
32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.8532
|
35 |
+
- Wer: 123.4043
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 7.5e-06
|
55 |
+
- train_batch_size: 4
|
56 |
+
- eval_batch_size: 2
|
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_ratio: 0.5
|
61 |
+
- training_steps: 2
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.8019 | 0.5 | 1 | 1.8532 | 123.4043 |
|
69 |
+
| 1.6763 | 1.0 | 2 | 1.8532 | 123.4043 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
73 |
|
74 |
+
- Transformers 4.27.3
|
75 |
+
- Pytorch 1.13.1+cu116
|
76 |
+
- Datasets 2.10.1
|
77 |
- Tokenizers 0.13.2
|