Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ This model is a fine-tuned version of `openai/whisper-small` on the wTIMIT-US da
|
|
| 19 |
|
| 20 |
It was evaluated on both normal and whispered speech subsets using Word Error Rate (WER) as the primary metric. While LF-Mask maintained comparable performance to SpecAugment, it did **not produce statistically significant improvements** in either speaking mode.
|
| 21 |
|
| 22 |
-
For a full explanation of the masking range and its acoustic motivation, refer to Section 3 of the **thesis**.
|
| 23 |
|
| 24 |
### Evaluation Results on wTIMIT-US (Test Set)
|
| 25 |
|
|
@@ -47,7 +47,7 @@ Available at: [https://campus-fryslan.studenttheses.ub.rug.nl/id/eprint/674](htt
|
|
| 47 |
### 🔗 Related Models
|
| 48 |
|
| 49 |
- [SpecAugment Baseline](https://huggingface.co/jankoko/SpecAugment-Whisper-small)
|
| 50 |
-
- [F0-Mask Version](https://huggingface.co/jankoko/PALF-
|
| 51 |
- [F1-Mask Version](https://huggingface.co/jankoko/PALF-F1-Whisper-small)
|
| 52 |
- [LF-Mask Version](https://huggingface.co/jankoko/PALF-LF-Whisper-small) ← current
|
| 53 |
|
|
|
|
| 19 |
|
| 20 |
It was evaluated on both normal and whispered speech subsets using Word Error Rate (WER) as the primary metric. While LF-Mask maintained comparable performance to SpecAugment, it did **not produce statistically significant improvements** in either speaking mode.
|
| 21 |
|
| 22 |
+
For a full explanation of the masking range and its acoustic motivation, refer to Section 3 of the **thesis linked below**.
|
| 23 |
|
| 24 |
### Evaluation Results on wTIMIT-US (Test Set)
|
| 25 |
|
|
|
|
| 47 |
### 🔗 Related Models
|
| 48 |
|
| 49 |
- [SpecAugment Baseline](https://huggingface.co/jankoko/SpecAugment-Whisper-small)
|
| 50 |
+
- [F0-Mask Version](https://huggingface.co/jankoko/PALF-Whisper-small)
|
| 51 |
- [F1-Mask Version](https://huggingface.co/jankoko/PALF-F1-Whisper-small)
|
| 52 |
- [LF-Mask Version](https://huggingface.co/jankoko/PALF-LF-Whisper-small) ← current
|
| 53 |
|