End of training
Browse files
README.md
CHANGED
@@ -8,9 +8,22 @@ tags:
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- yonisaka/asr_medical_id
|
|
|
|
|
11 |
model-index:
|
12 |
- name: whisper-small-id-v2
|
13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -19,6 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
# whisper-small-id-v2
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ASR Medical Indonesian dataset.
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,11 +60,14 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 500
|
47 |
-
- training_steps:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- yonisaka/asr_medical_id
|
11 |
+
metrics:
|
12 |
+
- wer
|
13 |
model-index:
|
14 |
- name: whisper-small-id-v2
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: ASR Medical Indonesian
|
21 |
+
type: yonisaka/asr_medical_id
|
22 |
+
args: 'config: id, split: test'
|
23 |
+
metrics:
|
24 |
+
- name: Wer
|
25 |
+
type: wer
|
26 |
+
value: 0.0
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
# whisper-small-id-v2
|
33 |
|
34 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ASR Medical Indonesian dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.0001
|
37 |
+
- Wer: 0.0
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
60 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_steps: 500
|
63 |
+
- training_steps: 1000
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:--------:|:----:|:---------------:|:---:|
|
70 |
+
| 0.0001 | 142.8571 | 1000 | 0.0001 | 0.0 |
|
71 |
|
72 |
|
73 |
### Framework versions
|