Downloads · 30 days
11
1% of all-time downloads
DrishtiSharma/wav2vec2-large-xls-r-300m-sat-a3
wav2vec2-large-xls-r-300m-sat-a3 is a automatic speech recognition model from DrishtiSharma. 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
11
1% of all-time downloads
All-time downloads
758
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 facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - SAT dataset. It achieves the following results on the evaluation set:
python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-sat-a3 --dataset mozilla-foundation/common_voice_8_0 --config sat --split test --log_outputs
Note: Santali (Ol Chiki) language not found in speech-recognition-community-v2/dev_data
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 11.1266 | 33.29 | 100 | 2.8577 | 1.0 |
| 2.1549 | 66.57 | 200 | 1.0799 | 0.5542 |
| 0.5628 | 99.86 | 300 | 0.7973 | 0.4016 |
| 0.0779 | 133.29 | 400 | 0.8424 | 0.4177 |
| 0.0404 | 166.57 | 500 | 0.9048 | 0.4137 |
| 0.0212 | 199.86 | 600 | 0.8961 | 0.3976 |