Downloads · 30 days
42
27% of all-time downloads
NadiaHolmlund/Japanese_Fine_Tuned_Whisper_Model
Japanese_Fine_Tuned_Whisper_Model is a automatic speech recognition model from NadiaHolmlund. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice dataset. It achieves the following results on the evaluation set: - Loss: 0.780524 - Wer: 301.625840
Downloads · 30 days
42
27% of all-time downloads
All-time downloads
155
Public
Repo size
756 MB
Likes
0
Public
Click a slice to open those files.
.bin151 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice dataset. It achieves the following results on the evaluation set:
The tiny Whisper model is fine-tuned on Japanese speech samples from the Common Voice dataset, based on which users can perform Automatic Speech Recognition in real time in Japanese.
The following hyperparameters were used during training:
| Training Loss | Step | Validation Loss | Wer |
|---|---|---|---|
| 0.4766 | 1000 | 0.739755 | 140.797746 |
| 0.3136 | 2000 | 0.720202 | 190.830262 |
| 0.1756 | 3000 | 0.773473 | 215.47997 |
| 0.1472 | 4000 | 0.780524 | 301.625840 |