Downloads · 30 days
0
banhchungtuongot/ffasr-base-beam4-decode
ffasr-base-beam4-decode is a automatic speech recognition model from banhchungtuongot. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Unmodified base weights (efficient-speech/lite-whisper-large-v3-turbo-acc). Decode = beam 4, lengthpenalty 0.6, norepeatngramsize 3. No LoRA / no adapter. Isolates the decode change vs the base greedy leaderboard entry.
Downloads · 30 days
0
Access
Public
Updated Jul 20, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.py2.1 KB · 52%
From the Hugging Face model README
Unmodified base weights (efficient-speech/lite-whisper-large-v3-turbo-acc). Decode = beam 4, length_penalty 0.6, no_repeat_ngram_size 3. No LoRA / no adapter. Isolates the decode change vs the base greedy leaderboard entry.