rnjema-unima/qwen3-tts-african-blindspots

Domain:

natural language processing

Record type:

dataset

Creator:

rnj

Host:

Model tested: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice import torch from qwen_tts import Qwen3TTSModel model = Qwen3TTSModel.from_pretrained( "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice", device_map="cuda:0", dtype=torch.bfloat16, ) wavs, sr = model.generate_custom_voice( text="...", language="Auto", speaker="Ryan" ) Platform: Google Colab T4 GPU (free tier).

Visit

huggingface.co

Tasks

speech processing text to speech

Loubna1101/Qwen3-TTS-Darija-1hour

# Qwen3-TTS-Darija-1hour A Darija Moroccan Arabic text-to-speech project based on **Qwen3-TTS-12Hz-

Loubna1101/Qwen3-TTS-Darija-LoRa

# Qwen3-TTS-Darija-LoRa A Darija Moroccan Arabic text-to-speech project based on **Qwen3-TTS-12Hz-1

ouilyh/qwen-blindspots-african-languages

This dataset documents failure cases of the base modelQwen3.5-0.8B. The model has approximately 0.8

rnjema/pythonday1_mwdsbc

Collaborative repo for Python Week of Code - Malawi Data Science Bootcamp 2021

rnjema/paRAleGal

An attempt at developing LLM-powered (RAFT-based) AI legal assistant for African Law # OpenLaw AI P

kedhamyas/my-blindspots-dataset

This dataset was created to probe blind spots in a small, recently released base language model by f