Downloads · 30 days
8
1% of all-time downloads
DrishtiSharma/xls-r-es-test-lm-finetuned-sentiment-mesd
xls-r-es-test-lm-finetuned-sentiment-mesd is a audio classification model from DrishtiSharma. 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
8
1% of all-time downloads
All-time downloads
733
Public
Repo size
3.8 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 glob-asr/xls-r-es-test-lm on the None dataset. It achieves the following results on the evaluation set:
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.86 | 3 | 1.7876 | 0.1923 |
| 1.9709 | 1.86 | 6 | 1.7869 | 0.2 |
| 1.9709 | 2.86 | 9 | 1.7859 | 0.2308 |
| 2.146 | 3.86 | 12 | 1.7851 | 0.2385 |
| 1.9622 | 4.86 | 15 | 1.7842 | 0.1923 |
| 1.9622 | 5.86 | 18 | 1.7834 | 0.1769 |
| 2.137 | 6.86 | 21 | 1.7823 | 0.1923 |
| 2.137 | 7.86 | 24 | 1.7812 | 0.1923 |
| 2.1297 | 8.86 | 27 | 1.7800 | 0.1846 |
| 1.9502 | 9.86 | 30 | 1.7787 | 0.1846 |
| 1.9502 | 10.86 | 33 | 1.7772 | 0.1846 |
| 2.1234 | 11.86 | 36 | 1.7760 | 0.1846 |
| 2.1234 | 12.86 | 39 | 1.7748 | 0.1846 |
| 2.1186 | 13.86 | 42 | 1.7736 | 0.1846 |
| 1.9401 | 14.86 | 45 | 1.7725 | 0.1846 |
| 1.9401 | 15.86 | 48 | 1.7715 | 0.1923 |
| 2.112 | 16.86 | 51 | 1.7706 | 0.1923 |
| 2.112 | 17.86 | 54 | 1.7701 | 0.1923 |
| 2.1094 | 18.86 | 57 | 1.7697 | 0.2 |
| 1.934 | 19.86 | 60 | 1.7696 | 0.2 |