Text-to-Speech
Transformers
Safetensors
Korean
English
qwen2
text-generation
text-generation-inference
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("jaeyong2/neutts-air-ko")
model = AutoModelForCausalLM.from_pretrained("jaeyong2/neutts-air-ko", device_map="auto")Quick Links
Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)
Install info
https://huggingface.co/neuphonic/neutts-air
Example
from neuttsair.neutts import NeuTTSAir
import soundfile as sf
tts = NeuTTSAir(backbone_repo="jaeyong2/neutts-air-ko-preview", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu")
input_text = "ํ๋๋์ด ์ธ์์ ์ด์ฒ๋ผ ์ฌ๋ํ์ฌ ๋
์์๋ฅผ ์ฃผ์
จ์ผ๋ ์ด๋ ์ ๋ฅผ ๋ฏฟ๋ ์๋ง๋ค ๋ฉธ๋ง์น ์๊ณ ์์์ ์ป๊ฒ ํ๋ ค ํ์ฌ์ด๋๋ผ"
ref_text = "train_000.txt"
ref_audio_path = "train_000.wav"
ref_text = open(ref_text, "r").read().strip()
ref_codes = tts.encode_reference(ref_audio_path)
wav = tts.infer(input_text, ref_codes, ref_text)
sf.write("new.wav", wav, 24000)
ref_audio (Bingsu/zeroth-korean)
jaeyong2/neutts-air-ko result
neuphonic/neutts-air result
License
- neuphonic/neutts-air : https://choosealicense.com/licenses/apache-2.0/
Acknowledgement
This research is supported by TPU Research Cloud program.
- Downloads last month
- 63
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="jaeyong2/neutts-air-ko")