Downloads · 30 days
23
4% of all-time downloads
infinitejoy/wav2vec2-large-xls-r-300m-finnish
wav2vec2-large-xls-r-300m-finnish 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
23
4% of all-time downloads
All-time downloads
519
Public
Repo size
20.2 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_7_0 - FI 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 |
|---|---|---|---|---|
| 2.9032 | 4.39 | 500 | 2.8768 | 1.0 |
| 1.5724 | 8.77 | 1000 | 0.5638 | 0.6438 |
| 1.1818 | 13.16 | 1500 | 0.3338 | 0.4759 |
| 1.0798 | 17.54 | 2000 | 0.2876 | 0.4086 |
| 1.0296 | 21.93 | 2500 | 0.2694 | 0.4248 |
| 1.0014 | 26.32 | 3000 | 0.2626 | 0.3733 |
| 0.9616 | 30.7 | 3500 | 0.2391 | 0.3294 |
| 0.9303 | 35.09 | 4000 | 0.2352 | 0.3218 |
| 0.9248 | 39.47 | 4500 | 0.2351 | 0.3207 |
| 0.8837 | 43.86 | 5000 | 0.2341 | 0.3103 |
| 0.8887 | 48.25 | 5500 | 0.2311 | 0.3115 |
| 0.8529 | 52.63 | 6000 | 0.2230 | 0.3001 |
| 0.8404 | 57.02 | 6500 | 0.2279 | 0.3054 |
| 0.8242 | 61.4 | 7000 | 0.2298 | 0.3006 |
| 0.8288 | 65.79 | 7500 | 0.2333 | 0.2997 |