Update README.md
Browse files
README.md
CHANGED
@@ -23,6 +23,9 @@ model-index:
|
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
value: 55.432891743610334
|
|
|
|
|
|
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,9 +34,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
# Whisper-small-thai
|
32 |
|
33 |
This model is a fine-tuned version of [biodatlab/whisper-th-small-combined](https://huggingface.co/biodatlab/whisper-th-small-combined) on the common_voice_17_0 dataset.
|
34 |
-
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.1073
|
36 |
-
- Wer: 55.4329
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -62,15 +62,7 @@ The following hyperparameters were used during training:
|
|
62 |
- training_steps: 5000
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
-
### Training results
|
66 |
|
67 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
-
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
69 |
-
| 0.3415 | 0.3647 | 1000 | 0.1371 | 65.4958 |
|
70 |
-
| 0.1638 | 0.7294 | 2000 | 0.1253 | 60.3238 |
|
71 |
-
| 0.1995 | 1.0941 | 3000 | 0.1161 | 57.4736 |
|
72 |
-
| 0.213 | 1.4588 | 4000 | 0.1104 | 56.2358 |
|
73 |
-
| 0.2041 | 1.8235 | 5000 | 0.1073 | 55.4329 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
@@ -78,4 +70,4 @@ The following hyperparameters were used during training:
|
|
78 |
- Transformers 4.43.3
|
79 |
- Pytorch 2.3.1+cu121
|
80 |
- Datasets 2.20.0
|
81 |
-
- Tokenizers 0.19.1
|
|
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
value: 55.432891743610334
|
26 |
+
language:
|
27 |
+
- th
|
28 |
+
pipeline_tag: automatic-speech-recognition
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
# Whisper-small-thai
|
35 |
|
36 |
This model is a fine-tuned version of [biodatlab/whisper-th-small-combined](https://huggingface.co/biodatlab/whisper-th-small-combined) on the common_voice_17_0 dataset.
|
|
|
|
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
62 |
- training_steps: 5000
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
|
|
65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
70 |
- Transformers 4.43.3
|
71 |
- Pytorch 2.3.1+cu121
|
72 |
- Datasets 2.20.0
|
73 |
+
- Tokenizers 0.19.1
|