Skip to content
Trending storyDeveloping

ModelScope releases PiVo-1.4M, a 1.4M-parameter English TTS model that runs on CPU

1 article1 sourcesince Nov 2Last article 9h ago ·

Overview

AISummary of 1 article

ModelScope releases PiVo-1.4M, an English text-to-speech model with 1.4M parameters and a built-in vocoder that generates 16 kHz mono speech.

The model runs offline on a CPU using NumPy and ONNX Runtime, without PyTorch. ModelScope reports a 0.532% word error rate on its held-out test set, a measure of intelligibility rather than naturalness. The code and acoustic weights are released under Apache-2.0.

Written by AI from the articles below · updated Nov 2, 5:10 AM ET

Check the sources:

Latest developmentNov 2, 5:00 AM ET
PiVo-1.4M: 1.4M-parameter English TTS that runs offline on CPU

Article timeline

The articles in this story. Times are ET.

Nov 2
  1. ModelScopeOfficial
    PiVo-1.4M: 1.4M-parameter English TTS that runs offline on CPU

    AIModelScope releases PiVo-1.4M, an English text-to-speech model with 1.4M parameters and a built-in vocoder that generates 16 kHz mono speech. It runs offline on CPU using NumPy and ONNX Runtime without PyTorch, and reaches a 0.532% WER on its held-out test set, a measure of intelligibility rather than naturalness.

    Video from @ModelScope2022's post

Heat Trend

Current comparable heat
8
Peak comparable heat
10Nov 2, 6:00 AM ET
Change in past 24 hours
–

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.