dscripka / synthetic_speech_dataset_generation
This repository contains text-to-speech (TTS) models and utilities designed produce synthetic training datasets for other speech-related models.
☆14Updated last year
Related projects ⓘ
Alternatives and complementary repositories for synthetic_speech_dataset_generation
- ☆16Updated 3 years ago
- 🎯 Speech Recognition Challenge by Speech Lab - IIT Madras☆11Updated 4 years ago
- ☆40Updated last year
- Goodness of Pronunciation algorithm using PyKaldi☆14Updated 2 years ago
- ☆10Updated last year
- ☆11Updated 3 years ago
- A simple, but performant framework for mapping speech directly to categories and intents.☆17Updated 3 months ago
- Evaluation of STT models for german language☆15Updated 2 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated 9 months ago
- Repository for reproducing result in journal "Self-supervised learning for Speech Emotion Recognition"☆9Updated last year
- Simple Python library, distributed via binary wheels with few direct dependencies, for easily using wav2vec 2.0 models for speech recogni…☆24Updated 3 years ago
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- ☆11Updated last year
- English ASR Challenge organized by Speech Lab, IIT Madras☆11Updated 3 years ago
- Indic-Conformer models for ASR☆15Updated 4 months ago
- A neural language modeling toolkit built on PyTorch☆18Updated last year
- Python bindings of speexdsp noise suppression library☆34Updated 2 years ago
- Multilingual acoustic word embedding approaches applied and evaluated on GlobalPhone data.☆10Updated 4 years ago
- A transcribed speech dataset in Wolof, Pulaar and Sereer, to support agriculture. Funded by Lacuna Fund.☆13Updated 6 months ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- DUSTED: Spoken-Term Discovery using Discrete Speech Units☆13Updated last month
- ☆41Updated last year
- Speech to text transcription using RNN (Listen, Attend and Spell).☆11Updated 5 years ago
- EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting☆23Updated 2 years ago
- This repo contains the baseline model recipes and pre-trained model for GramVanni hindi ASR challenge☆14Updated 2 years ago
- A handy dataset of noises for ASR☆19Updated 5 years ago
- ☆9Updated last month
- A pipeline to isolate and transcribe one language in mixed-language speech☆18Updated 2 years ago
- ☆12Updated 3 years ago
- [Interspeech22]Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Ass…☆22Updated 9 months ago