Downloads · 30 days
5
10% of all-time downloads
jayashreedevi2020/wav2vec2-large-xls-r-300m-assamese_speech_to_IPA_new
wav2vec2-large-xls-r-300m-assamese_speech_to_IPA_new is a automatic speech recognition model from jayashreedevi2020. 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
10% of all-time downloads
All-time downloads
50
Public
Parameters
315M
6.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 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_11_0 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 |
|---|---|---|---|---|
| 5.375 | 9.8765 | 400 | 0.8566 | 0.9870 |
| 0.2819 | 19.7531 | 800 | 0.7781 | 0.9481 |
| 0.0973 | 29.6296 | 1200 | 0.7538 | 0.9156 |