Downloads · 30 days
42
23% of all-time downloads
sarasarasara/whisper-tiny-finetuned-bmd-V8-fp16-20241111_170957-LOSO-section-out1
whisper-tiny-finetuned-bmd-V8-fp16-20241111_170957-LOSO-section-out1 is a audio classification model from sarasarasara. Use it for the audio classification task on the model card, and read the license before you ship it in a product. 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
42
23% of all-time downloads
All-time downloads
185
Public
Parameters
8.3M
432 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors33.2 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-tiny on an unknown 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.8571 | 3 | 1.1392 | 0.1724 | 0.0507 |
| No log | 2.0 | 7 | 1.2490 | 0.1724 | 0.0507 |
| 1.0669 | 2.8571 | 10 | 1.2255 | 0.3103 | 0.2037 |
| 1.0669 | 4.0 | 14 | 1.3051 | 0.3103 | 0.2067 |
| 1.0669 | 4.8571 | 17 | 1.2610 | 0.3103 | 0.2026 |
| 0.7916 | 6.0 | 21 | 1.4744 | 0.4138 | 0.3766 |
| 0.7916 | 6.8571 | 24 | 1.6646 | 0.3448 | 0.2309 |
| 0.7916 | 8.0 | 28 | 1.6063 | 0.4138 | 0.4224 |
| 0.2845 | 8.8571 | 31 | 2.0461 | 0.4138 | 0.4324 |
| 0.2845 | 10.0 | 35 | 1.9449 | 0.3793 | 0.3710 |
| 0.2845 | 10.8571 | 38 | 2.4039 | 0.3793 | 0.4124 |
| 0.0571 | 12.0 | 42 | 2.7720 | 0.3103 | 0.3145 |
| 0.0571 | 12.8571 | 45 | 2.8264 | 0.3448 | 0.3276 |
| 0.0571 | 14.0 | 49 | 3.1613 | 0.3448 | 0.2926 |
| 0.012 | 14.8571 | 52 | 3.3470 | 0.3448 | 0.3240 |
| 0.012 | 16.0 | 56 | 3.4096 | 0.3103 | 0.3056 |
| 0.012 | 16.8571 | 59 | 3.4095 | 0.3103 | 0.3056 |
| 0.0059 | 17.1429 | 60 | 3.4075 | 0.3103 | 0.3056 |