Downloads · 30 days
4
44% of all-time downloads
platypus123/onevoice-sensevoice-en-construction-v1
onevoice-sensevoice-en-construction-v1 is a automatic speech recognition model from platypus123. Use it when you need speech turned into text. The card lists the license as other.
Fine-tuned English ASR checkpoint used by OneVoice V2. The evaluated checkpoint is model.pt (uploaded from model.pt.ep10).
Downloads · 30 days
4
44% of all-time downloads
All-time downloads
9
Public
Repo size
1 GB
Likes
0
Public
Click a slice to open those files.
.pt1 GB · 100%
From the Hugging Face model README
Fine-tuned English ASR checkpoint used by OneVoice V2. The evaluated checkpoint is model.pt (uploaded from model.pt.ep10).
Held-out synthetic EN test: clean WER 0.374%; noisy WER 0.545%. This is a research/demo artifact trained on synthetic speech and construction-noise augmentation, not a real-site production claim. Use with the matching FunASR/SenseVoice training configuration.