EndlessReform / smolttsLinks
Open TTS models, built for streaming on the edge
ā43Updated 7 months ago
Alternatives and similar repositories for smoltts
Users that are interested in smoltts are comparing it to the libraries listed below
Sorting:
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.ā68Updated last week
- šļø Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets āØā128Updated 2 months ago
- Audio tokenization, in the fastest way possible!ā53Updated last year
- ā62Updated last year
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GPā¦ā102Updated last year
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.ā104Updated 3 weeks ago
- StyleTTS 2 Optimized Training Forkā34Updated 8 months ago
- Collection of Open Source Speech Dataā161Updated 3 weeks ago
- Official implementation of the TTS model Lina-Speechā170Updated 9 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.ā19Updated 11 months ago
- Code associated with the paper: CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition.ā15Updated 5 months ago
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.ā43Updated last month
- LongCat Audio Tokenizer and Detokenizerā178Updated last week
- [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximationā132Updated 5 months ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.ā27Updated last year
- VoiceBox neural network implementationā110Updated last year
- Joint speech-language model - respond directly to audio!ā30Updated last year
- A collection of all our phonemeizers for dataset construction and inferenceā27Updated 8 months ago
- An unofficial PyTorch implementation of VALL-Eā88Updated 2 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jaxā15Updated last year
- š¼ Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decompositionā15Updated last year
- A TTS model that makes a speaker speak new languagesā76Updated last year
- ā50Updated last week
- ā59Updated last year
- Open-source reproducible benchmarks from Argmaxā65Updated last week
- ā100Updated 3 weeks ago
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latencyā159Updated this week
- This repository contains the code and data for the paper EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control by Haozhe Chen,ā¦ā80Updated last year
- ā19Updated 7 months ago
- The YouTube Text-To-Speech dataset is comprised of waveform audio extracted from YouTube videos alongside their English transcriptionsā51Updated 4 years ago