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 ์„ธ์ƒ์„ ์ด์ฒ˜๋Ÿผ ์‚ฌ๋ž‘ํ•˜์‚ฌ ๋…์ƒ์ž๋ฅผ ์ฃผ์…จ์œผ๋‹ˆ ์ด๋Š” ์ €๋ฅผ ๋ฏฟ๋Š” ์ž๋งˆ๋‹ค ๋ฉธ๋ง์น˜ ์•Š๊ณ  ์˜์ƒ์„ ์–ป๊ฒŒ ํ•˜๋ ค ํ•˜์‹ฌ์ด๋‹ˆ๋ผ"

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

Acknowledgement

This research is supported by TPU Research Cloud program.

Downloads last month
163
Safetensors
Model size
0.6B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for jaeyong2/neutts-air-ko

Finetuned
(9)
this model
Quantizations
1 model