Akshit Arora aroraakshit

ICASSP 2023 LIMMITS CHALENGE SUBMISSION FOR VANI: VERY-LIGHTWEIGHT ACCENT-CONTROLLABLE TTS FOR NATIVE AND NON-NATIVE SPEAKERS WITH IDENTITY PRESERVATION

This gist includes:

Speaker	Initial data points	Duplicates, empty audio or transcripts	Final data points	Initial Durations of final data points (hours)	Final Durations after silence removal (hours)
Hindi_M	17798	1	17797	40.49	39.63
Hindi_F	16512	29	16483	40.21	38.16
Telugu_M	16939	0

	import numpy as np

	def softmax(x):
	""" Compute the softmax for each row of the input x
	Arguments:
	x -- A N dimensional veector or M X N dimensional numpy matrix.
	Return:
	x -- modified x in-place
	"""

	#!/bin/bash

	OS_NAME=$(lsb_release -is \| tr '[:upper:]' '[:lower:]')
	readonly OS_NAME
	OS_DIST=$(lsb_release -cs)
	readonly OS_DIST
	CUDA_VERSION='10.2'
	readonly CUDA_VERSION

	readonly DEFAULT_NVIDIA_DEBIAN_GPU_DRIVER_VERSION='460.56'

	#!/bin/bash

	# Dataproc configurations
	readonly HADOOP_CONF_DIR='/etc/hadoop/conf'
	readonly HIVE_CONF_DIR='/etc/hive/conf'
	readonly SPARK_CONF_DIR='/etc/spark/conf'

	function execute_with_retries() {
	local -r cmd=$1
	for ((i = 0; i < 10; i++)); do