Instructions to use mesolitica/Malaysian-TTS-1.7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mesolitica/Malaysian-TTS-1.7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="mesolitica/Malaysian-TTS-1.7B-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mesolitica/Malaysian-TTS-1.7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("mesolitica/Malaysian-TTS-1.7B-v0.1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mesolitica/Malaysian-TTS-1.7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mesolitica/Malaysian-TTS-1.7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/Malaysian-TTS-1.7B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mesolitica/Malaysian-TTS-1.7B-v0.1

SGLang

How to use mesolitica/Malaysian-TTS-1.7B-v0.1 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/Malaysian-TTS-1.7B-v0.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/Malaysian-TTS-1.7B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Malaysian-TTS-1.7B-v0.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mesolitica/Malaysian-TTS-1.7B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mesolitica/Malaysian-TTS-1.7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/mesolitica/Malaysian-TTS-1.7B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A newer version of this model is available: mesolitica/Malaysian-TTS-1.7B-v1

Malaysian-TTS-1.7B-v0.1

Continue pretraining Qwen/Qwen3-1.7B-Base on mesolitica/Malaysian-TTS-v2,

Use DistilCodec as speech detokenizer, output in 24k sample rate.
Optional controllable pitch and speed for each words.
Support context switching between Malay and English.
Support streamable text segment.
Support husein and idayu speakers only.

How do we train

Dataset purely synthetic generated using mesolitica/Malaysian-Podcast-Dia-1.6B.
Multipacking with proper document masking on 4096 context length.
FP32-BF16 mixed precision training.
Full parameter finetuning.
WanDB at https://wandb.ai/huseinzol05/Qwen-Qwen3-1.7B-Base-4k-TTS-distilcodec

How to use

First install DistilCodec,

pip3 install git+https://github.com/mesolitica/DistilCodec

Load the models,

# wget https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0/resolve/main/model_config.json
# wget https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0/resolve/main/g_00204000

from distilcodec import DistilCodec, demo_for_generate_audio_codes
from transformers import AutoTokenizer, AutoModelForCausalLM

codec_model_config_path='model_config.json'
codec_ckpt_path = 'g_00204000'

codec = DistilCodec.from_pretrained(
    config_path=codec_model_config_path,
    model_path=codec_ckpt_path,
    use_generator=True,
    is_debug=False).eval()

tokenizer = AutoTokenizer.from_pretrained('mesolitica/Malaysian-TTS-1.7B-v0.1')
model = AutoModelForCausalLM.from_pretrained('mesolitica/Malaysian-TTS-1.7B-v0.1', torch_dtype = 'auto').cuda()

Non-streaming

import soundfile as sf

string = 'The first anti-hoax legislation in the world, Akta Anti Berita Tidak Benar two thousand and eighteen. Saya nak makan nasi ayam.'
left = 'idayu' +': ' + string
prompt = f'<|im_start|>{left}<|speech_start|>'

generate_kwargs = dict(
    **tokenizer(prompt, return_tensors = 'pt', add_special_tokens = False).to('cuda'),
    max_new_tokens=1024,
    temperature=0.5,
    do_sample=True,
    repetition_penalty=1.0,
)
generation_output = model.generate(**generate_kwargs)
speech_token = tokenizer.decode(generation_output[0]).split('<|speech_start|>')[1].replace('<|endoftext|>', '')
numbers = re.findall(r'speech_(\d+)', speech_token)
d = list(map(int, numbers))
y_gen = codec.decode_from_codes(d, minus_token_offset=False)
sf.write('output.mp3', y_gen[0, 0].cpu().numpy(), 24000)

Output,

Streaming text context

from tqdm import tqdm
import numpy as np

strings = [
  'The first anti-hoax legislation in the world,',
  'Akta Anti Berita Tidak Benar two thousand and eighteen.',
  'Saya nak makan nasi ayam,',
  'dan saya tak suka mandi.'
]

ys = []
generation_output = None

for no, string in tqdm(enumerate(strings)):
    if generation_output is None:
        left = 'streaming,idayu' +': ' + string
        prompt = f'<|im_start|>{left}<|speech_start|>'
    else:
        left = string
        prompt = f'{tokenizer.decode(generation_output[0])}{left}<|speech_start|>'
    generate_kwargs = dict(
        **tokenizer(prompt, return_tensors = 'pt', add_special_tokens = False).to('cuda'),
        max_new_tokens=1024,
        temperature=0.6,
        do_sample=True,
        repetition_penalty=1.,
    )
    generation_output = model.generate(**generate_kwargs)
    speech_token = tokenizer.decode(generation_output[0]).split('<|speech_start|>')[-1].replace('<|endoftext|>', '')
    numbers = re.findall(r'speech_(\d+)', speech_token)
    d = list(map(int, numbers))
    y_gen = codec.decode_from_codes(
        d, 
        minus_token_offset=False
    )
    ys.append(y_gen[0, 0].cpu().numpy())

sf.write('output.mp3', np.concatenate(ys), 24000)