Downloads · 30 days
13
4% of all-time downloads
anuragshas/wav2vec2-xls-r-300m-pa-IN-cv8-with-lm
wav2vec2-xls-r-300m-pa-IN-cv8-with-lm is a automatic speech recognition model from anuragshas. 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
13
4% of all-time downloads
All-time downloads
357
Public
Repo size
24 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-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - PA-IN 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 |
|---|---|---|---|---|
| 4.3322 | 14.81 | 400 | 3.7450 | 1.0 |
| 3.2662 | 29.63 | 800 | 3.2571 | 0.9996 |
| 1.6408 | 44.44 | 1200 | 0.9098 | 0.8162 |
| 1.2289 | 59.26 | 1600 | 0.6757 | 0.7099 |
| 1.0551 | 74.07 | 2000 | 0.6417 | 0.7044 |
| 0.966 | 88.89 | 2400 | 0.6365 | 0.6789 |
| 0.8713 | 103.7 | 2800 | 0.6617 | 0.6954 |
| 0.8055 | 118.52 | 3200 | 0.6371 | 0.6762 |
| 0.7489 | 133.33 | 3600 | 0.6798 | 0.6911 |
| 0.7073 | 148.15 | 4000 | 0.6567 | 0.6731 |
| 0.6609 | 162.96 | 4400 | 0.6742 | 0.6840 |
| 0.6435 | 177.78 | 4800 | 0.6862 | 0.6633 |
| 0.6282 | 192.59 | 5200 | 0.6865 | 0.6731 |