Fasih-TTS-V1

Home/Models/NightPrince/Fasih-TTS-V1

NightPrince/Fasih-TTS-V1

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-to-speech
root model: coqui/XTTS-v2
provider: NightPrince
license: other
language: ar
context: —
library: coqui
vRAM (GB): —
size on disk: —
downloads: 307
likes: 2
created: —
last modified: 2026-07-09T18:38:11+00:00 (2026)
huggingface: https://huggingface.co/NightPrince/Fasih-TTS-V1
tags: coquitext-to-speechttsarabicarabic-ttsfushamsaxttsxtts-v2speech-synthesisvoice-cloningardataset:NightPrince/Arabic-professional-original-voicedataset:NightPrince/Fasih-TTS-Benchmarkbase_model:coqui/XTTS-v2base_model:finetune:coqui/XTTS-v2license:othermodel-indexregion:us

benchmark	category	score	conf	evidence
WER	speech-asr	6.5	low	`\| Fasih-TTS-V1 (ours) \| 6.5 \| 2.5 \| 3.16 \|`
UTMOS	speech-tts	3.16	low	`\| Fasih-TTS-V1 (ours) \| 6.5 \| 2.5 \| 3.16 \|`
CER	speech-asr	1.3	low	`\| Varied MSA sentences \| 8 \| 1.3% \| 2.2% \|`

none scraped.