Downloads · 30 days
0
amber-hadra-webgpu
Sakuragaoka/amber-hadra-webgpu
amber-hadra-webgpu is a text-to-speech model from Sakuragaoka. Use it when you need text read aloud. It is set up for onnxruntime. The card lists the license as apache-2.0.
Browser-oriented ONNX conversion of Jip7e/habibi-tts-doda-darija for ONNX Runtime Web with WebGPU.
Access
Public
Updated Sep 8, 2026
Repo size
992 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx992 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- onnxruntime
- License
- apache-2.0
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026
- SHA
- 06f0bd9f
Base models
Model card
From the Hugging Face model README
HADRA Moroccan Darija WebGPU ONNX
Browser-oriented ONNX conversion of
Jip7e/habibi-tts-doda-darija
for ONNX Runtime Web with WebGPU.
This repository does not contain a separately trained voice model. It converts
the official HADRA F5-TTS weights into an encoder, FP16 transformer, and decoder
used by the Amber browser client. The included F1.wav reference is Salma, the
official F1 reference voice, paired with the transcript:
هوما مخبيين شي حاجة انا متيقن
Files
encoder_fp32.onnxtransformer_fp16.onnxdecoder_fp32.onnxvocab.txtF1.wav
Attribution
HADRA is an Apache-2.0 Moroccan Darija fine-tune of Habibi-TTS/F5-TTS published by the HADRA authors and trained on DODa Moroccan Arabic speech. See the upstream model card for architecture, dataset, usage, and citation details.
- Task
- Text-to-Speech
- Library
- onnxruntime
- License
- apache-2.0
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026