nguyen-brat/nguyen-ngoc-ngan-vieneu-tts-fine-tune

# System packages (Ubuntu/Debian)
sudo apt-get install -y build-essential cmake libsndfile1 ffmpeg

# Install Rust (needed for sea-g2p phonemizer)
curl https://sh.rustup.rs -sSf | sh -s -- -y
source ~/.cargo/env

# Python packages
pip install vieneu soundfile numpy

from vieneu import Vieneu
import soundfile as sf

# Load the fine-tuned model (auto-downloads from HF Hub)
tts = Vieneu(backbone_repo="nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned")

# Generate speech
audio = tts.infer("Xin chao, day la giong noi tieng Viet duoc tong hop bang AI.")
sf.write("output.wav", audio, samplerate=24000)
print("Saved output.wav")

import torch
from vieneu import Vieneu

device = "cuda" if torch.cuda.is_available() else "cpu"
tts = Vieneu(
    backbone_repo="nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned",
    backbone_device=device,
    codec_device=device,
)
audio = tts.infer("Xin chao the gioi!")

# Extra dependency for GGUF
pip install llama-cpp-python transformers huggingface-hub

from huggingface_hub import hf_hub_download
from llama_cpp import Llama
from transformers import AutoTokenizer
from vieneu import Vieneu
import soundfile as sf
import numpy as np

# --- Config ---
REPO = "nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned"
SPEECH_OFFSET = 151671  # <|speech_0|> token ID
SPEECH_END    = 151670  # <|SPEECH_GENERATION_END|> token ID
SPEECH_MAX    = 65535

# --- Step 1: Load model components ---
gguf_path = hf_hub_download(repo_id=REPO, filename="vieneu_q4_k_m.gguf")

# n_gpu_layers=-1 for full GPU offload, 0 for CPU-only
llm = Llama(model_path=gguf_path, n_gpu_layers=0, n_ctx=32768, verbose=False)
tokenizer = AutoTokenizer.from_pretrained(REPO)
vieneu = Vieneu(backbone_repo=REPO)  # for codec + phonemizer + voices

# --- Step 2: Prepare input ---
text = "Xin chao, day la giong noi tieng Viet."

# Get a preset voice (or use ref_audio for voice cloning)
voice = vieneu.get_preset_voice()  # uses default voice
ref_codes = voice["codes"]
ref_text  = voice.get("text", "")

# Normalize and phonemize
from vieneu_utils.phonemize_text import phonemize_with_dict
text_normalized = vieneu.normalizer.normalize(text)
ref_phonemes    = vieneu.get_ref_phonemes(ref_text)
chunk_phonemes  = phonemize_with_dict(text_normalized, skip_normalize=True)

# --- Step 3: Build prompt ---
codes_str = "".join(f"<|speech_{int(c)}|>" for c in ref_codes.flatten())
prompt = (
    f"user: Convert the text to speech:"
    f"<|TEXT_PROMPT_START|>{ref_phonemes} {chunk_phonemes}<|TEXT_PROMPT_END|>\n"
    f"assistant:<|SPEECH_GENERATION_START|>{codes_str}"
)
prompt_ids = tokenizer.encode(prompt, add_special_tokens=False)

# --- Step 4: Generate speech tokens ---
speech_ids = []
for token_id in llm.generate(prompt_ids, top_k=50, temp=1.0, reset=True):
    # Ignore end token until at least 50 speech tokens collected
    if token_id == SPEECH_END and len(speech_ids) >= 50:
        break
    if SPEECH_OFFSET <= token_id <= SPEECH_OFFSET + SPEECH_MAX:
        speech_ids.append(token_id)
    if len(speech_ids) >= 16000:
        break

# --- Step 5: Decode to audio ---
decode_str = "".join(f"<|speech_{tid - SPEECH_OFFSET}|>" for tid in speech_ids)
audio = vieneu._decode(decode_str)
sf.write("output.wav", audio, samplerate=24000)
print(f"Generated {len(audio)/24000:.1f}s of audio ({len(speech_ids)} tokens)")

from vieneu import Vieneu
import soundfile as sf

tts = Vieneu(backbone_repo="nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned")

audio = tts.infer(
    text="Ngay xua, co mot chu be ten la An song trong mot ngoi lang nho ven song.",
    ref_audio="reference.wav",          # 3-10 second WAV of target speaker
    ref_text="Transcript of reference.", # optional but improves quality
)
sf.write("cloned.wav", audio, samplerate=24000)

from vieneu import Vieneu

tts = Vieneu(backbone_repo="nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned")

# List available voices
for display_name, key in tts.list_preset_voices():
    print(f"  {key}: {display_name}")

# Use a specific preset
voice = tts.get_preset_voice("binh")  # binh | tuyen | nguyen | huong | ngoc | doan
audio = tts.infer(text="Xin chao!", voice=voice)

from vieneu import Vieneu
import soundfile as sf

tts = Vieneu(backbone_repo="nguyen-brat/VieNeu-TTS-Vietnamese-Finetuned")

story = """Ngay xua, co mot chu be ten la An song trong mot ngoi lang nho ven song.

Moi sang, An thuong day som de giup me ganh nuoc va nau com.
Cau thich nhat la duoc chay ra bo song, ngoi ngam nhung con ca boi loi duoi lan nuoc trong vat."""

# Synthesize each chunk (max 100 chars) with pauses between sentences/paragraphs
chunks = []
for i in range(0, len(story), 200):
    chunk = story[i:i+200].strip()
    if chunk:
        audio = tts.infer(chunk)
        chunks.append(audio)

import numpy as np
silence = np.zeros(int(24000 * 0.3))  # 300ms pause
full_audio = np.concatenate([np.concatenate([c, silence]) for c in chunks])
sf.write("story.wav", full_audio, samplerate=24000)