Downloads · 30 days
10
2% of all-time downloads
Santiagot1105/wav2vec2-large-xlsr-finetune-es-col
wav2vec2-large-xlsr-finetune-es-col is a automatic speech recognition model from Santiagot1105. 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
10
2% of all-time downloads
All-time downloads
411
Public
Repo size
5 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 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 |
|---|---|---|---|---|
| 4.9709 | 3.25 | 400 | 2.9673 | 1.0 |
| 2.9488 | 6.5 | 800 | 2.9075 | 0.9973 |
| 2.907 | 9.76 | 1200 | 2.8772 | 0.9688 |
| 2.886 | 13.01 | 1600 | 2.8245 | 0.9484 |
| 2.8043 | 16.26 | 2000 | 2.7134 | 0.9874 |
| 2.7288 | 19.51 | 2400 | 2.6750 | 0.9874 |
| 2.7072 | 22.76 | 2800 | 2.6651 | 0.9874 |
| 2.6892 | 26.02 | 3200 | 2.6573 | 0.9874 |
| 2.683 | 29.27 | 3600 | 2.6514 | 0.9874 |