Downloads · 30 days
4
13% of all-time downloads
luyotw/openfun-ivod-whisper-large-v3-LaiShiBao-10-104
openfun-ivod-whisper-large-v3-LaiShiBao-10-104 is a automatic speech recognition model from luyotw. Use it when you need speech turned into text. It is set up for transformers.
- 原始模型: openai/whisper-large-v3 - 使用音訊數量: 17696 - 使用音訊總長: 9.42 小時 - 音訊平均長度: 1.92 秒 - GPU: NVIDIA H100 PCIe x 1 - 訓練時間: 02:08:15 - 模型大小: 5.75 GB - 訓練參數: - batch size: 80 - eval batch size: 40 - gradient checkpointing:…
Downloads · 30 days
4
13% of all-time downloads
All-time downloads
30
Public
Parameters
1.5B
92.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt61.7 GB · 62%
From the Hugging Face model README
openai/whisper-large-v3NVIDIA H100 PCIe x 1This model is a fine-tuned version of openai/whisper-large-v3 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 | Wer |
|---|---|---|---|---|
| 0.0235 | 0.4505 | 100 | 0.0248 | 80.4383 |
| 0.0178 | 0.9009 | 200 | 0.0237 | 78.6807 |
| 0.0156 | 1.3514 | 300 | 0.0236 | 78.7948 |
| 0.0173 | 1.8018 | 400 | 0.0234 | 78.4068 |
| 0.0121 | 2.2523 | 500 | 0.0235 | 78.2926 |