lucasnewman / e2-tts-mlxLinks
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX
☆20Updated 11 months ago
Alternatives and similar repositories for e2-tts-mlx
Users that are interested in e2-tts-mlx are comparing it to the libraries listed below
Sorting:
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆27Updated 11 months ago
- Implementation of 'Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis', in MLX☆22Updated 10 months ago
- Open TTS models, built for streaming on the edge☆42Updated 6 months ago
- A simple, hackable text-to-speech system in PyTorch and MLX☆174Updated last month
- ☆62Updated last year
- Joint speech-language model - respond directly to audio!☆30Updated last year
- Audio tokenization, in the fastest way possible!☆53Updated last year
- StyleTTS 2 Optimized Training Fork☆33Updated 7 months ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆68Updated last week
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆123Updated last month
- Find out why your CoreML model isn't running on the Neural Engine!☆26Updated last year
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆57Updated 4 months ago
- Training Models Daily☆17Updated last year
- VoiceBox neural network implementation☆110Updated last year
- ☆246Updated 2 weeks ago
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated last year
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆68Updated last month
- ☆107Updated last year
- Collection of Open Source Speech Data☆160Updated this week
- Open-source reproducible benchmarks from Argmax☆58Updated last week
- StyleTTS2 + Vocos as a Decoder☆13Updated 5 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆15Updated last year
- Ultra-minimal autoregressive diffusion model for image generation☆19Updated 11 months ago
- ☆117Updated 2 months ago
- ☆140Updated 3 weeks ago
- ☆40Updated this week
- Voxtral: Convert Mistral into a end2end SpeechLM. No information bottleneck, preserves prosody, learns interruptions from data. Unlike GP…☆30Updated 6 months ago
- (WIP) A retrain of F5-TTS on permissively-licensed data☆12Updated 5 months ago
- Speaker Diarization with Transformers☆69Updated 3 months ago
- Supervoice diffusion enhance☆27Updated last year