Downloads · 30 days
97
7% of all-time downloads
YonaKhine/finetuned-w2v2-bert-burmese-asr
finetuned-w2v2-bert-burmese-asr is a automatic speech recognition model from YonaKhine. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
97
7% of all-time downloads
All-time downloads
1.5K
Public
Parameters
606M
4.8 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors2.4 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the OpenSLR-80 Burmese Speech Dataset 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 |
|---|---|---|---|---|
| 0.2901 | 4.1678 | 300 | 0.4585 | 0.5053 |
| 0.2127 | 8.3357 | 600 | 0.3886 | 0.4256 |
You can listen to an example where a user says:
မင်္ဂလာ ပါ တွေ့ရတာဝမ်းသာပါတယ် ရှင်
မင်္ဂလာ ပါ တွေ့ရတာ ဝမ်းသပါတယ် ရှင်
မင်္ဂလာ ပါ တွေ့ရတာဝမ်းသာပါတယ် ရှင်
WER ≈ 0.10 – minor vowel difference only, excellent semantic preservation.
Download and listen: burmese_test.wav