Downloads · 30 days
4
3% of all-time downloads
HouraMor/wav2vec2-ft-lre4-admw-ga2b16-vocab
wav2vec2-ft-lre4-admw-ga2b16-vocab is a automatic speech recognition model from HouraMor. 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
4
3% of all-time downloads
All-time downloads
141
Public
Parameters
315M
7.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt5 GB · 57%
From the Hugging Face model README
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-english 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 | Cer |
|---|---|---|---|---|---|
| 3.414 | 0.4165 | 1000 | 3.4982 | 1.0000 | 1.0000 |
| 3.3068 | 0.8330 | 2000 | 3.4475 | 1.0000 | 1.0000 |
| 3.2394 | 1.2495 | 3000 | 3.3492 | 1.0000 | 1.0000 |
| 3.1938 | 1.6660 | 4000 | 3.2937 | 1.0005 | 0.9935 |
| 2.9202 | 2.0825 | 5000 | 2.9150 | 0.9960 | 0.7484 |
| 2.7715 | 2.4990 | 6000 | 2.7814 | 0.9496 | 0.6761 |
| 2.6715 | 2.9155 | 7000 | 2.7571 | 0.9254 | 0.6105 |
| 2.6394 | 3.3319 | 8000 | 2.6561 | 0.9036 | 0.5877 |
| 2.4635 | 3.7484 | 9000 | 2.5670 | 0.8816 | 0.5829 |
| 2.4659 | 4.1649 | 10000 | 2.6025 | 0.8883 | 0.5673 |