neuphonic/neutts-air
Text-to-Speech
β’
0.7B
β’
Updated
β’
19.6k
β’
841
torchaoInt8WeightOnlyConfig is already working flawlessly in our tests.import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_
pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)
@spaces.GPU
def generate(prompt: str):
return pipeline(prompt).images[0]State-of-the-art target speech extractor
Extreme Super-Resolution via Scale Autoregression
Generate 3D models from text descriptions
Watch and experiment with realtime AIβs with visuals
Voice Activity Detection using MarbleNet model
Filter multilingual data for high-quality language models
Transcribe speech and highlight emphasized words