DarijaTTS-v0.1-500M/README.md

library_name, tags, license, language, datasets, base_model, pipeline_tag

library_name	tags	license	language	datasets	base_model	pipeline_tag
transformers	unsloth trl sft tts	apache-2.0	ary	KandirResearch/DarijaTTS-clean	OuteAI/OuteTTS-0.2-500M	text-to-speech

Moroccan Darija TTS

This is a text-to-speech (TTS) model for Moroccan Darija, fine-tuned from OuteAI/OuteTTS-0.2-500M on the KandirResearch/DarijaTTS-clean dataset.

Model Details

• Base Model: OuteAI/OuteTTS-0.2-500M
• Dataset: KandirResearch/DarijaTTS-clean
• Training Method: Fine-tuned using Unsloth's SFTTrainer
• Dataset Preparation: Preprocessed following OuteTTS training guide
• Demo: Try it here

Usage

Important

Compatibility Note Recent updates to outetts have introduced breaking changes. If you encounter the error: AttributeError: module 'outetts' has no attribute 'GGUFModelConfig_v2'

Solution: Please install a compatible version (0.3.3 or 0.3.2) to resolve this:

pip install outetts==0.3.3

You can run the model using outetts as follows:

Install outetts and llama-cpp-python:

pip install outetts==0.3.3 llama-cpp-python huggingface_hub

import outetts
from outetts.models.config import GenerationConfig
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(
    repo_id="KandirResearch/DarijaTTS-v0.1-500M",
    filename="unsloth.Q8_0.gguf",
)
model_config = outetts.GGUFModelConfig_v2(
    model_path=model_path,
    tokenizer_path="KandirResearch/DarijaTTS-v0.1-500M",
)
interface = outetts.InterfaceGGUF(model_version="0.3", cfg=model_config)

def tts(text, temperature=0.3, repetition_penalty=1.1):
    gen_cfg = GenerationConfig(
        text=text,
        temperature=temperature,
        repetition_penalty=repetition_penalty,
        max_length=4096,
    )
    output = interface.generate(config=gen_cfg)
    output_path = "output.wav"
    output.save(output_path)
    return output_path

# Example usage
audio_path = tts("السلام كيداير لاباس عليك؟")
print(f"Generated audio saved at: {audio_path}")

Training

The model was fine-tuned using Unsloth's SFTTrainer. The dataset was preprocessed following the OuteTTS training guide. LoRA-based fine-tuning was applied to improve efficiency.

Support Me

---

For any issues or improvements, feel free to open a discussion or PR!