VoiceTut-TTS

Home/Models/mohammedaly22/VoiceTut-TTS

mohammedaly22/VoiceTut-TTS

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-to-speech
root model: k2-fsa/OmniVoice
provider: mohammedaly22
license: apache-2.0
language: ar, arz, en
context: —
library: omnivoice
vRAM (GB): —
size on disk: —
downloads: 450
likes: 11
created: —
last modified: 2026-06-30T08:55:22+00:00 (2026)
huggingface: https://huggingface.co/mohammedaly22/VoiceTut-TTS
tags: omnivoicesafetensorstext-to-speechttsegyptian-arabicarabiccode-switchingvoice-cloningararzenbase_model:k2-fsa/OmniVoicebase_model:finetune:k2-fsa/OmniVoicelicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
Speaker SIM	speech-tts	83.0	Speaker similarity (cloning, cosine)	medium	`\| Speaker similarity (cloning, cosine) \| 0.83 \|`
WER	speech-asr	40.0	WER — Egyptian Arabic	medium	`\| WER — Egyptian Arabic \| 0.40 \|`
WER	speech-asr	7.0	WER — English	medium	`\| WER — English \| 0.07 \|`
UTMOS	speech-tts	3.47	Naturalness (UTMOS, 1–5)	medium	`\| Naturalness (UTMOS, 1–5) \| 3.47 \|`

none scraped.