README.md

metadata

title: Nawah ASR 50M
emoji: 🎧
colorFrom: blue
colorTo: indigo
sdk: docker
app_port: 7860
pinned: false
short_description: تفريغ صوتي عربي بموديل Emhotob 50M

Nawah-ASR-50M

Arabic ASR where a 50M Arabic LLM writes the transcript. A frozen Whisper-small encoder feeds a 0.39M projector; oddadmix/50M-2048-Emhotob does the generating.

Record or upload a clip (up to 30s). The demo reports the audio token count, which tracks the clip's real duration at 25 tokens/sec -- a 3-second clip costs 75 tokens, not the 375 a fixed 30-second window would spend on silence.

Scored on a 3,165-clip video-disjoint MASC split (same clips, same normalizer for every row):

model	decoder	WER	CER
openai/whisper-small (zero-shot)	Whisper 153M	0.5739	0.2062
whisper-small-arabic-dialectal	Whisper 153M	0.6775	0.2244
Nawah-ASR-50M-v1 (60 h)	Emhotob 50M	0.6145	0.2936
Nawah-ASR-50M-v1.1 (300 h)	Emhotob 50M	0.4109	0.1815

With the encoder fixed, swapping Whisper's 153M decoder for Emhotob's 50M takes WER 0.5739 -> 0.4109. Caveat: this is MASC's home turf and both Whisper checkpoints are out-of-domain here -- the tell is that the dialect-tuned one scores worse than the base model on this MSA-leaning data.

Model: oddadmix/Nawah-ASR-50M-v1.1