Pinned Repositories
alignments
Automatically creates/downloads alignments for multiple speech datasets, using pre-existing alignments were possible.
lco
Light Config for research code, MVPs and prototypes.
LightningFastSpeech2
opensubtitles-dataloader
Loads OpenSubtitles v2018 dataset without having to load everything into memory at once. Works well with pytorch.
phones
A collection of utilities for handling IPA phones.
poooli
A python library for printing on the Poooli thermal printer.
punctuation-iwslt2011
Huggingface datasets script for pre-processing punctuation annotation using IWSLT11 dataset.
simple-back
A simple daily python backtester that works out of the box.
vagrant-lamp-craft
Starting point for developing a site powered by Craft CMS with Vagrant.
ttsds
The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these factors with real speech and noise datasets.
MiniXC's Repositories
MiniXC/alignments
Automatically creates/downloads alignments for multiple speech datasets, using pre-existing alignments were possible.
MiniXC/speech-collator
A collator for speech datasets with different batching strategies and attribute extraction.
MiniXC/simple_hifigan
MiniXC/minixc.github.io
My own website.
MiniXC/MPM
Maked Prosody Model
MiniXC/speech-datasets
Preprocessing pipeline for speech datasets.
MiniXC/tts-for-asr-report
MiniXC/ttsdb
MiniXC/charsiu
Charsiu: A neural phonetic aligner.
MiniXC/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
MiniXC/diff_from_scratch
MiniXC/fairseq-noconf
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
MiniXC/FastPitchesForCirrus
Deep Learning Examples
MiniXC/fictag-visualizer
MiniXC/libriheavy-small
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context (only small split)
MiniXC/masked-prosody-modeling
A masked prosody model.
MiniXC/masked-prosody-modeling-evaluation
A masked prosody model & it's evaluation on downstream tasks.
MiniXC/masked_prosody_model
MiniXC/miipher-3.9
Unofficial implementation of miipher
MiniXC/ml-template
Template for my machine learning projects.
MiniXC/mnist-cirrus
MiniXC/Montreal-Forced-Aligner-3.12-fix
Command line utility for forced alignment using Kaldi
MiniXC/opentts-leaderboard
MiniXC/phonemizer-object
Simple text to phones converter for multiple languages - using an object instead of a function
MiniXC/prob-mse-diff
MiniXC/TPUses
MiniXC/ttsdb-data
MiniXC/victorian-tree-party
MiniXC/vocex2
Vocex with whisper encoder and additional targets.
MiniXC/whisper-no-triton
Robust Speech Recognition via Large-Scale Weak Supervision (without triton)