Downloads · 30 days
6
22% of all-time downloads
nkkbr/whisper-large-v3-zatoichi-ja-EX-4-TRAIN_2_TO_10_EVAL_1
whisper-large-v3-zatoichi-ja-EX-4-TRAIN_2_TO_10_EVAL_1 is a automatic speech recognition model from nkkbr. 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
22% of all-time downloads
All-time downloads
27
Public
Parameters
1.5B
24.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-large-v3 on the None 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 |
|---|---|---|---|---|
| 1.143 | 0.1316 | 5 | 0.9593 | 99.4792 |
| 0.7372 | 0.2632 | 10 | 0.7673 | 112.5 |
| 0.5888 | 0.3947 | 15 | 0.6384 | 80.2083 |
| 0.5928 | 0.5263 | 20 | 0.6101 | 83.3333 |
| 0.6567 | 0.6579 | 25 | 0.5899 | 83.0729 |
| 0.5552 | 0.7895 | 30 | 0.5595 | 81.7708 |
| 0.5951 | 0.9211 | 35 | 0.5429 | 88.1076 |
| 0.4835 | 1.0526 | 40 | 0.5348 | 78.9931 |
| 0.4183 | 1.1842 | 45 | 0.5464 | 85.7639 |
| 0.3745 | 1.3158 | 50 | 0.5513 | 80.6424 |
| 0.3297 | 1.4474 | 55 | 0.5246 | 78.5590 |
| 0.3144 | 1.5789 | 60 | 0.5277 | 86.8056 |
| 0.3702 | 1.7105 | 65 | 0.5243 | 86.2847 |
| 0.4006 | 1.8421 | 70 | 0.5213 | 74.4792 |
| 0.337 | 1.9737 | 75 | 0.5229 | 81.6840 |
| 0.2173 | 2.1053 | 80 | 0.5140 | 80.6424 |
| 0.2251 | 2.2368 | 85 | 0.5282 | 76.3021 |
| 0.2248 | 2.3684 | 90 | 0.5439 | 76.0417 |
| 0.1808 | 2.5 | 95 | 0.5405 | 74.6528 |
| 0.2443 | 2.6316 | 100 | 0.5433 | 77.4306 |
| 0.2175 | 2.7632 | 105 | 0.5406 | 75.3472 |
| 0.2371 | 2.8947 | 110 | 0.5404 | 82.7257 |
| 0.1125 | 3.0263 | 115 | 0.5456 | 83.6806 |
| 0.1197 | 3.1579 | 120 | 0.5472 | 73.9583 |
| 0.1401 | 3.2895 | 125 | 0.5642 | 76.2153 |
| 0.1275 | 3.4211 | 130 | 0.5724 | 77.7778 |
| 0.1248 | 3.5526 | 135 | 0.5737 | 77.6042 |
| 0.1392 | 3.6842 | 140 | 0.5762 | 77.8646 |
| 0.1084 | 3.8158 | 145 | 0.5774 | 79.7743 |
| 0.1819 | 3.9474 | 150 | 0.5761 | 79.4271 |