Downloads · 30 days
27
4% of all-time downloads
DrishtiSharma/wav2vec2-large-xls-r-300m-maltese
wav2vec2-large-xls-r-300m-maltese 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
27
4% of all-time downloads
All-time downloads
690
Public
Repo size
17.7 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 - MT 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 |
|---|---|---|---|---|
| 3.0174 | 9.01 | 1000 | 3.0552 | 1.0 |
| 1.0446 | 18.02 | 2000 | 0.6708 | 0.7577 |
| 0.7995 | 27.03 | 3000 | 0.4202 | 0.4770 |
| 0.6978 | 36.04 | 4000 | 0.3054 | 0.3494 |
| 0.6189 | 45.05 | 5000 | 0.2878 | 0.3154 |
| 0.5667 | 54.05 | 6000 | 0.3114 | 0.3286 |
| 0.5173 | 63.06 | 7000 | 0.3085 | 0.3021 |
| 0.4682 | 72.07 | 8000 | 0.3058 | 0.2969 |
| 0.451 | 81.08 | 9000 | 0.3146 | 0.2907 |
| 0.4213 | 90.09 | 10000 | 0.3030 | 0.2881 |
| 0.4005 | 99.1 | 11000 | 0.3001 | 0.2789 |
!python eval.py
--model_id DrishtiSharma/wav2vec2-large-xls-r-300m-maltese
--dataset mozilla-foundation/common_voice_8_0 --config mt --split test --log_outputs