Use the NGC CLI to download:
Copied!
Resource
The Tacotron 2 and WaveGlow model form a text-to-speech system that enables user to synthesise a natural sounding speech from raw transcripts.
Use the NGC CLI to download:
Copied!
Changelog
June 2020
- Updated performance tables to include A100 results
March 2020
- Added Tacotron 2 and WaveGlow inference using TensorRT Inference Server with custom TensorRT backend in
trtis_cpp - Added Conversational AI demo script in
notebooks/conversationalai - Fixed loading CUDA RNG state in
load_checkpoint()function intrain.py - Fixed FP16 export to TensorRT in
trt/README.md
January 2020
- Updated batch sizes and performance results for Tacotron 2.
December 2019
- Added export and inference scripts for TensorRT. See Tacotron2 TensorRT README.
November 2019
- Implemented training resume from checkpoint
- Added notebook for running Tacotron 2 and WaveGlow in TRTIS.
October 2019
- Tacotron 2 inference with torch.jit.script
September 2019
- Introduced inference statistics
August 2019
- Fixed inference results
- Fixed initialization of Batch Normalization
July 2019
- Changed measurement units for Tacotron 2 training and inference performance benchmarks from input tokes per second to output mel-spectrograms per second
- Introduced batched inference
- Included warmup in the inference script
June 2019
- AMP support
- Data preprocessing for Tacotron 2 training
- Fixed dropouts on LSTMCells
March 2019
- Initial release
Known issues
There are no known issues in this release.