End of training
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ base_model: openai/whisper-small
|
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
- fruk19/
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
@@ -17,14 +17,14 @@ model-index:
|
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: aicookcook
|
20 |
-
type: fruk19/
|
21 |
config: default
|
22 |
split: None
|
23 |
args: 'config: th'
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
-
value:
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aicookcook dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer:
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -61,15 +61,15 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 1000
|
64 |
-
- num_epochs:
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
70 |
-
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- fruk19/S_SMALL
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
|
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: aicookcook
|
20 |
+
type: fruk19/S_SMALL
|
21 |
config: default
|
22 |
split: None
|
23 |
args: 'config: th'
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 17.728859060402684
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aicookcook dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.1606
|
38 |
+
- Wer: 17.7289
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 1000
|
64 |
+
- num_epochs: 5
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
71 |
+
| 0.1544 | 2.0 | 6000 | 0.1638 | 20.1799 |
|
72 |
+
| 0.0584 | 4.0 | 12000 | 0.1606 | 17.7289 |
|
73 |
|
74 |
|
75 |
### Framework versions
|
runs/Jun21_18-48-21_fruk19pc/events.out.tfevents.1718970502.fruk19pc.13940.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf606f93b18687693c188c017bb6a7ad6480a7aa9dda7f4fe9171f7ca6d8438
|
3 |
+
size 39187
|