Instructions to use mesolitica/malay-parler-tts-mini-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mesolitica/malay-parler-tts-mini-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mesolitica/malay-parler-tts-mini-v1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("mesolitica/malay-parler-tts-mini-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mesolitica/malay-parler-tts-mini-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mesolitica/malay-parler-tts-mini-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/malay-parler-tts-mini-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mesolitica/malay-parler-tts-mini-v1

SGLang

How to use mesolitica/malay-parler-tts-mini-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mesolitica/malay-parler-tts-mini-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/malay-parler-tts-mini-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mesolitica/malay-parler-tts-mini-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/malay-parler-tts-mini-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mesolitica/malay-parler-tts-mini-v1 with Docker Model Runner:
```
docker model run hf.co/mesolitica/malay-parler-tts-mini-v1
```

Malay Parler TTS Mini V1

Finetuned https://huggingface.co/parler-tts/parler-tts-mini-v1 on Malay TTS dataset

Source code at https://github.com/mesolitica/malaya-speech/tree/master/session/parler-tts

Wandb at https://wandb.ai/huseinzol05/parler-speech?nw=nwuserhuseinzol05

requirements

pip3 install git+https://github.com/mesolitica/async-parler-tts

how to

import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

device = "cuda:0" if torch.cuda.is_available() else "cpu"

model = ParlerTTSForConditionalGeneration.from_pretrained("mesolitica/malay-parler-tts-mini-v1").to(device)
tokenizer = AutoTokenizer.from_pretrained("mesolitica/malay-parler-tts-mini-v1")

speakers = [
    'Yasmin',
    'Osman',
    'Bunga',
    'Ariff',
    'Ayu',
    'Kamarul',
    'Danial',
    'Elina',
]

prompt = 'Husein zolkepli sangat comel dan kacak suka makan cendol'

for s in speakers:
    description = f"{s}'s voice, delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."

    input_ids = tokenizer(description, return_tensors="pt").to(device)
    prompt_input_ids = tokenizer(prompt, return_tensors="pt").to(device)

    generation = model.generate(
      input_ids=input_ids.input_ids,
      attention_mask=input_ids.attention_mask,
      prompt_input_ids=prompt_input_ids.input_ids,
      prompt_attention_mask=prompt_input_ids.attention_mask,
    )

    audio_arr = generation.cpu()
    sf.write(f'{s}.mp3', audio_arr.numpy().squeeze(), 44100)

Downloads last month: 172

Safetensors

Model size

0.9B params

Tensor type

F32

Dataset used to train mesolitica/malay-parler-tts-mini-v1

Collection including mesolitica/malay-parler-tts-mini-v1

Malaysian Text-to-Speech

Collection

Malaysian Text-to-Speech models. • 28 items • Updated Sep 15, 2025 • 4