Te Hiku Media's repositories
Kaitiakitanga-License
Repository for the development of the Kaitiakitanga License
korero-maori-demos
A collection of demonstrations using the Kōrero Māori API
wahi-korero
Tools for creating audio segments suitable for captioning.
nga-tautohetohe
Code for extracting Māori text from the New Zealand Hansard
srt-streamer
SRT streaming code for use in AXIA Livewire, and other Audio over IP AOIP networks.
DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
nga-tautohetohe-reo
Corpus of Te Reo derived from the New Zealand Hansard
reo-toolkit
A python package for manipulating māori language text
icecast-deploy
Ansible playbook to deploy icecast2 in AWS
libretime-scripts
Scripts that we use to help with ingesting media into our LibreTime radio automation system.
api-playground
A playground to tutu with Papa Reo APIs
bert
TensorFlow code and pre-trained models for BERT
coqui_tts
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
django-chunked-upload
Upload large files to Django in multiple chunks, with the ability to resume if the upload is interrupted.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
ffmpeg-normalize
Audio Normalization for Python/ffmpeg
glasbey
Generate maximally distinct sets of colors
libretime
LibreTime: Radio Broadcast & Automation Platform
libretime-deploy
Ansible based deployment for LibreTime in the cloud (AWS)
pipelines
Machine Learning Pipelines for Kubeflow
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
STT-align
Coqui STT (🐸STT) based forced alignment tool
tensorflow
Computation using data flow graphs for scalable machine learning
wse-plugin-s3compatibleupload
Wowza Streaming Engine™ module that uses the AWS Java SDK to automatically upload recorded media files to an S3 compatible object store.