Hi team,
I am using Riva with model TTS FastPitch+HifiGan. I see in the command
riva-build speech_synthesis has parameters:
[–denoiser.max_sequence_idle_microseconds DENOISER.MAX_SEQUENCE_IDLE_MICROSECONDS]
** [–denoiser.max_batch_size DENOISER.MAX_BATCH_SIZE]**
** [–denoiser.min_batch_size DENOISER.MIN_BATCH_SIZE]**
** [–denoiser.opt_batch_size DENOISER.OPT_BATCH_SIZE]**
** [–denoiser.preferred_batch_size DENOISER.PREFERRED_BATCH_SIZE]**
** [–denoiser.batching_type DENOISER.BATCHING_TYPE]**
** [–denoiser.preserve_ordering DENOISER.PRESERVE_ORDERING]**
** [–denoiser.instance_group_count DENOISER.INSTANCE_GROUP_COUNT]**
** [–denoiser.max_queue_delay_microseconds DENOISER.MAX_QUEUE_DELAY_MICROSECONDS]**
** [–denoiser.optimization_graph_level DENOISER.OPTIMIZATION_GRAPH_LEVEL]**
** [–denoiser.fade_length DENOISER.FADE_LENGTH]**
when I don’t set the parameters as above, I saw in the config.pbtxt file in the models/tts_postprocessor the parameter use_denoiser=False
Hence any way to use denoiser in Riva!
Thanks!
Hardware - GPU (A100/A30/T4/V100)
Hardware - CPU
Operating System
Riva Version
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)