Automatic Speech Recognition
PEFT
Safetensors
Urdu
English
whisper
audio
speech-to-text
asr
translation
urdu
english
whisper-medium
lora
fast-inference
specdox
Instructions to use Shzaib/SpecDox-Whisper-Medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Shzaib/SpecDox-Whisper-Medium with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -45,7 +45,7 @@ The table below outlines the performance of the fine-tuned SpecDox models agains
|
|
| 45 |
|
| 46 |
| Model | WER% ↓ | BLEU ↑ | METEOR ↑ | BERTScore F1 ↑ | Rank |
|
| 47 |
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 48 |
-
| **
|
| 49 |
| Faster Whisper (SpecDox) | 36.28 | 53.24 | **0.7811** | 0.9402 | **#2** |
|
| 50 |
| Whisper Large-v3 | 42.88 | 46.86 | 0.7105 | 0.9270 | #3 |
|
| 51 |
| Whisper Medium (Baseline) | 45.33 | 44.16 | 0.6882 | 0.9226 | #4 |
|
|
|
|
| 45 |
|
| 46 |
| Model | WER% ↓ | BLEU ↑ | METEOR ↑ | BERTScore F1 ↑ | Rank |
|
| 47 |
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 48 |
+
| **SpecDox-Whisper-Medium** | **36.25** | **53.30** | 0.7804 | **0.9405** | **#1** |
|
| 49 |
| Faster Whisper (SpecDox) | 36.28 | 53.24 | **0.7811** | 0.9402 | **#2** |
|
| 50 |
| Whisper Large-v3 | 42.88 | 46.86 | 0.7105 | 0.9270 | #3 |
|
| 51 |
| Whisper Medium (Baseline) | 45.33 | 44.16 | 0.6882 | 0.9226 | #4 |
|