Downloads · 30 days
5
8% of all-time downloads
Motahar/wav2vec2-large-xls-r-300m-turkish-colab
wav2vec2-large-xls-r-300m-turkish-colab is a automatic speech recognition model from Motahar. 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
5
8% of all-time downloads
All-time downloads
66
Public
Repo size
12.6 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 common_voice 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 |
|---|---|---|---|---|
| 3.8894 | 3.67 | 400 | 0.7272 | 0.7232 |
| 0.4265 | 7.34 | 800 | 0.4567 | 0.5033 |
| 0.1963 | 11.01 | 1200 | 0.4435 | 0.4511 |
| 0.1288 | 14.68 | 1600 | 0.3897 | 0.3773 |
| 0.0976 | 18.35 | 2000 | 0.4021 | 0.3502 |
| 0.079 | 22.02 | 2400 | 0.4140 | 0.3473 |
| 0.0646 | 25.69 | 2800 | 0.3993 | 0.3255 |
| 0.0502 | 29.36 | 3200 | 0.3864 | 0.3077 |