Popular GitHub Repositories for Phonetic Transcriptions

PPG-Based Voice Conversion

Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts

Global Rhythm Style Transfer Without Text Transcriptions

Abydos NLP/IR library for Python

Foreign Accent Conversion by Synthesizing Speech from Phonetic Posteriorgrams (Interspeech'19)

NLP Functions for amplifying negations, managing elisions, creating ngrams, stems, phonetic codes to tokens and more.

High-Fidelity Neural Phonetic Posteriorgrams

Telegram bot to generate transcriptions and summarise voice notes

Web app enabling users to either record or upload audio files. Then utilizing OpenAI API (Whisper, GPT4) generates transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Users can also intelligently chat about their transcriptions with a GPT4 chatbot. Data is stored relationally in SQLite and also vectorized in Pinecone.

Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.

Automate call transcriptions for real-time and previously recorded calls by using custom speech models, text analytics, and industry-specific natural language processing with the Microsoft Call Center Intelligence Accelerator.

A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis

Dataset of ICASSP 2021 MULTILINGUAL PHONETIC DATASET FOR LOW RESOURCE SPEECH RECOGNITION

Evaluate results from ASR/Speech-to-Text quickly

The Open Source AI Musical Toolkit

Zero-Shot Foreign Accent Conversion without a Native Reference

Suite for phonetic word embeddings, especially their evaluation and baseline models.

Python Hindi Concatenative Based TTS using Phoneme Database

Voice Notes with AI transcriptions and post processing

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition