LongCat-AudioDiT：波形 latent 空间中的高保真扩散文本转语音

pip install -r requirements.txt

# TTS
python inference.py --text "今天晴暖转阴雨，空气质量优至良，空气相对湿度较低。" --output_audio output.wav --model_dir meituan-longcat/LongCat-AudioDiT-1B

# Voice cloning
python inference.py \
    --text "今天晴暖转阴雨，空气质量优至良，空气相对湿度较低。" \
    --prompt_text "小偷却一点也不气馁，继续在抽屉里翻找。" \
    --prompt_audio assets/prompt.wav \
    --output_audio output.wav \
    --model_dir meituan-longcat/LongCat-AudioDiT-1B \
    --guidance_method apg

# Batch inference (SeedTTS eval format, one item per line: uid|prompt_text|prompt_wav_path|gen_text)
python batch_inference.py \
    --lst /path/to/meta.lst \
    --output_dir /path/to/output \
    --model_dir meituan-longcat/LongCat-AudioDiT-1B \
    --guidance_method apg

import audiodit  # auto-registers with transformers
from audiodit import AudioDiTModel
from transformers import AutoTokenizer
import torch, soundfile as sf

# Load model
model = AudioDiTModel.from_pretrained("meituan-longcat/LongCat-AudioDiT-1B").to("cuda")
model.vae.to_half()  # VAE runs in fp16 (matching original)
model.eval()

tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder_model)

# Zero-shot synthesis
inputs = tokenizer(["今天晴暖转阴雨，空气质量优至良，空气相对湿度较低。"], padding="longest", return_tensors="pt")
output = model(
    input_ids=inputs.input_ids,
    attention_mask=inputs.attention_mask,
    duration=62,  # latent frames
    steps=16,
    cfg_strength=4.0,
    guidance_method="cfg",  # or "apg"
    seed=1024,
)
sf.write("output.wav", output.waveform.squeeze().cpu().numpy(), 24000)

import librosa, torch

# Load prompt audio
audio, _ = librosa.load("assets/prompt.wav", sr=24000, mono=True)
prompt_wav = torch.from_numpy(audio).unsqueeze(0).unsqueeze(0)  # (1, 1, T)

# Concatenate prompt_text + gen_text for the text encoder
prompt_text = "小偷却一点也不气馁，继续在抽屉里翻找。"
gen_text = "今天晴暖转阴雨，空气质量优至良，空气相对湿度较低。"
inputs = tokenizer([f"{prompt_text} {gen_text}"], padding="longest", return_tensors="pt")

output = model(
    input_ids=inputs.input_ids,
    attention_mask=inputs.attention_mask,
    prompt_audio=prompt_wav,
    duration=138,  # prompt_frames + gen_frames
    steps=16,
    cfg_strength=4.0,
    guidance_method="apg",
    seed=1024,
)