From db6a96543f926ee141787f6cf3a02748214128b3 Mon Sep 17 00:00:00 2001 From: liuyibing01 Date: Tue, 10 Mar 2020 04:55:12 +0000 Subject: [PATCH] Update README --- README.md | 28 ++++++++++++++-------------- examples/waveflow/README.md | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index 4d51be4..69452b7 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-spee In particular, it features the latest [WaveFlow] (https://arxiv.org/abs/1912.01219) model proposed by Baidu Research. - WaveFlow can synthesize 22.05 kHz high-fidelity speech around 40x faster than real-time on a Nvidia V100 GPU without engineered inference kernels, which is faster than [WaveGlow] (https://github.com/NVIDIA/waveglow) and serveral orders of magnitude faster than WaveNet. -- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M) and comparable to WaveNet (4.6M). +- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M). - WaveFlow is directly trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet, which simplifies the training pipeline and reduces the cost of development. ## Overview @@ -100,26 +100,26 @@ Parakeet also releases some well-trained parameters for the example models, whic
+ +

+ +

-
- + +
+
+ - + **Note:** The input samples are drawn from validation dataset that are not visible in training. - TTS models diff --git a/examples/waveflow/README.md b/examples/waveflow/README.md index d36f0f3..d42d71e 100644 --- a/examples/waveflow/README.md +++ b/examples/waveflow/README.md @@ -3,7 +3,7 @@ PaddlePaddle dynamic graph implementation of [WaveFlow: A Compact Flow-based Model for Raw Audio](https://arxiv.org/abs/1912.01219). - WaveFlow can synthesize 22.05 kHz high-fidelity speech around 40x faster than real-time on a Nvidia V100 GPU without engineered inference kernels, which is faster than [WaveGlow] (https://github.com/NVIDIA/waveglow) and serveral orders of magnitude faster than WaveNet. -- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M) and comparable to WaveNet (4.6M). +- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M). - WaveFlow is directly trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet, which simplifies the training pipeline and reduces the cost of development. ## Project Structure -- GitLab