Downloads · 30 days
11
2% of all-time downloads
infinitejoy/wav2vec2-large-xls-r-300m-abkhaz-cv8
wav2vec2-large-xls-r-300m-abkhaz-cv8 is a automatic speech recognition model from infinitejoy. 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
2% of all-time downloads
All-time downloads
727
Public
Repo size
16.4 GB
Likes
2
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 - AB 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 |
|---|---|---|---|---|
| 1.2881 | 4.26 | 4000 | 0.3764 | 0.6461 |
| 1.0767 | 8.53 | 8000 | 0.2657 | 0.5164 |
| 0.9841 | 12.79 | 12000 | 0.2330 | 0.4445 |
| 0.9274 | 17.06 | 16000 | 0.2134 | 0.3929 |
| 0.8781 | 21.32 | 20000 | 0.1945 | 0.3886 |
| 0.8381 | 25.59 | 24000 | 0.1840 | 0.3737 |
| 0.8054 | 29.85 | 28000 | 0.1756 | 0.3523 |
| 0.7763 | 34.12 | 32000 | 0.1745 | 0.3299 |
| 0.7474 | 38.38 | 36000 | 0.1677 | 0.3074 |
| 0.7298 | 42.64 | 40000 | 0.1649 | 0.2963 |
| 0.7125 | 46.91 | 44000 | 0.1617 | 0.2931 |