Text-to-Speech
Transformers
Safetensors
Portuguese
English
qwen2
text-generation
text-generation-inference
Instructions to use jaeyong2/neutts-air-pt-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jaeyong2/neutts-air-pt-preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="jaeyong2/neutts-air-pt-preview")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jaeyong2/neutts-air-pt-preview") model = AutoModelForCausalLM.from_pretrained("jaeyong2/neutts-air-pt-preview") - Notebooks
- Google Colab
- Kaggle
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-pt-preview", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu")
input_text = "Porque Deus amou o mundo de tal maneira que deu o seu Filho unigênito, para que todo aquele que nele crê não pereça, mas tenha a vida eterna."
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 (yuriyvnv/synthetic_transcript_pt)
jaeyong2/neutts-air-pt 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
- 4