Spaces:
Running on Zero
Download README.md from anwar-dev/bayan-arabic-tts: direct link, hf CLI and curl.
- Browser
- Download file 2.5 kB
-
https://huggingface.co/spaces/anwar-dev/bayan-arabic-tts/resolve/main/README.md
- Command line
-
hf download hf://spaces/anwar-dev/bayan-arabic-tts/README.md
-
curl -L -o README.md https://huggingface.co/spaces/anwar-dev/bayan-arabic-tts/resolve/main/README.md
A newer version of the Gradio SDK is available: 6.32.0
title: Bayan Arabic TTS
emoji: ๐๏ธ
colorFrom: indigo
colorTo: red
sdk: gradio
sdk_version: 6.31.0
app_file: app.py
python_version: '3.12'
startup_duration_timeout: 1h
short_description: Arabic TTS with the fine-tuned Bayan "Murad" voice
pinned: false
license: other
license_name: nvidia-open-model-license
license_link: https://huggingface.co/nvidia/magpie_tts_multilingual_357m
models:
- anwar-dev/Bayan-Arabic-TTS-v1.0
- nvidia/magpie_tts_multilingual_357m
๐๏ธ Bayan Arabic TTS (ุจูุงู)
Arabic text-to-speech with a single male voice โ ยซู
ุฑุงุฏยป / Murad โ built on
nvidia/magpie_tts_multilingual_357m
with LoRA fine-tuning and a dedicated baked speaker row.
- ๐ค Model weights: anwar-dev/Bayan-Arabic-TTS-v1.0
- ๐ค Base model: nvidia/magpie_tts_multilingual_357m
- ๐๏ธ Codec: NVIDIA NanoCodec 22.05 kHz
Type Arabic text, press ุชูููุฏ ุงูุตูุช ยท Generate speech, and get 22.05 kHz mono audio back. Use the Voice dropdown to compare the fine-tuned Murad voice (the default) against the five original MagpieTTS voices.
Tips for good results
- Diacritics matter. Training used fully diacritized (ู ุดูููุฉ) text. Undiacritized text still works, but accuracy is much better with the diacritics โ especially on word endings.
- Keep utterances under ~37 seconds; split longer passages.
- Text normalization is off (matching the authors' reference settings), so write numbers and symbols out as words.
- Stuttering? Lower Temperature toward
0.5or raise CFG scale toward3.0in the advanced settings.
Implementation notes
This Space loads the author's merged, self-contained Bayan-Arabic-TTS-v1.0.nemo
directly through NeMo's load_magpie_model (no separate load_lora_weights step),
with speaker_index=5, language="ar-MSA", cfg_scale=2.5, temperature=0.6,
topk=80. The example prompts are the author's own diacritized MSA sentences from
samples/msa/texts.txt in the model repo.
License
Derived from nvidia/magpie_tts_multilingual_357m and governed by the
NVIDIA Open Model License.
See the model repo's NOTICE.md for commercial-use terms.