zenlm/zen3-audio-fast

Zen3 Audio Fast

Fast variant of Zen3 Audio optimized for low-latency speech synthesis.

Overview

Built on Zen MoDE (Mixture of Distilled Experts) architecture with 500M parameters.

Developed by Hanzo AI and the Zoo Labs Foundation.

Quick Start

from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
import torch

model_id = "zenlm/zen3-audio-fast"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

# Load audio
import librosa
audio, sr = librosa.load("audio.wav", sr=16000)
inputs = processor(audio, sampling_rate=sr, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs)
print(processor.batch_decode(outputs, skip_special_tokens=True)[0])

Model Details

Attribute	Value
Parameters	500M
Architecture	Zen MoDE
Context	30s audio
License	Apache 2.0

License

Apache 2.0