PATTARA TIPAKSORN
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -42,7 +42,7 @@ print(text)
|
|
42 |
```
|
43 |
|
44 |
## Evaluation Performance
|
45 |
-
WER calculated with newmm tokenizer for Thai segmentation.
|
46 |
| Model | CV18 (WER) | Gowejee (WER) | LOTUS-TRD (WER) | Thai Dialect (WER) | Elderly (WER) | Gigaspeech2 (WER) | Fleurs (WER) | Distant Meeting (WER) | Podcast (WER) |
|
47 |
|:----------------------------------------|:----------------------:|:-------------------------:|:----------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|
|
48 |
| whisper-large-v3 | 18.75 | 46.59 | 48.14 | 57.82 | 12.27 | 33.26 | 24.08 | 72.57 | 41.24 |
|
@@ -51,7 +51,7 @@ WER calculated with newmm tokenizer for Thai segmentation.
|
|
51 |
| monsoon-whisper-medium-gigaspeech2 | 11.66 | 20.50 | 41.04 | 42.06 | 7.57 | 21.40 | 21.54 | 51.65 | 38.89 |
|
52 |
| pathumma-whisper-th-large-v3 | 8.68 | 9.84 | 15.47 | 19.85 | 1.53 | 21.66 | 15.65 | 51.56 | 36.47 |
|
53 |
|
54 |
-
**Note:**
|
55 |
|
56 |
## Limitations
|
57 |
More information needed
|
|
|
42 |
```
|
43 |
|
44 |
## Evaluation Performance
|
45 |
+
WER calculated with newmm tokenizer for Thai word segmentation.
|
46 |
| Model | CV18 (WER) | Gowejee (WER) | LOTUS-TRD (WER) | Thai Dialect (WER) | Elderly (WER) | Gigaspeech2 (WER) | Fleurs (WER) | Distant Meeting (WER) | Podcast (WER) |
|
47 |
|:----------------------------------------|:----------------------:|:-------------------------:|:----------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|
|
48 |
| whisper-large-v3 | 18.75 | 46.59 | 48.14 | 57.82 | 12.27 | 33.26 | 24.08 | 72.57 | 41.24 |
|
|
|
51 |
| monsoon-whisper-medium-gigaspeech2 | 11.66 | 20.50 | 41.04 | 42.06 | 7.57 | 21.40 | 21.54 | 51.65 | 38.89 |
|
52 |
| pathumma-whisper-th-large-v3 | 8.68 | 9.84 | 15.47 | 19.85 | 1.53 | 21.66 | 15.65 | 51.56 | 36.47 |
|
53 |
|
54 |
+
**Note:** Other models not target fine-tuned on dialect datasets may be less representative of dialect performance.
|
55 |
|
56 |
## Limitations
|
57 |
More information needed
|