Downloads · 30 days
6
18% of all-time downloads
IoanaLiviaPopescu/real-data-synth-data-1200-1-Standard-B-whisper-small-v0
real-data-synth-data-1200-1-Standard-B-whisper-small-v0 is a automatic speech recognition model from IoanaLiviaPopescu. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
6
18% of all-time downloads
All-time downloads
34
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-small on the IoanaLiviaPopescu/RealVoiceSynthVoice-1200-1-Standard-B dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0 | 0 | 0.6024 | 27.8812 |
| 0.2756 | 1.0 | 51 | 0.4008 | 18.0712 |
| 0.1052 | 2.0 | 102 | 0.3728 | 17.4073 |
| 0.055 | 3.0 | 153 | 0.3760 | 16.8357 |
| 0.0322 | 4.0 | 204 | 0.3911 | 17.3889 |
| 0.0226 | 5.0 | 255 | 0.4034 | 17.6286 |