Video wird geladen...
Video konnte nicht geladen werden
You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks. Unsloth makes TTS training 1.5x faster with 50% less VRAM. GitHub: Docs & Notebooks:
126,420 Aufrufe • vor 1 Jahr •via X (Twitter)
11 Kommentare

Can it be multilingual?

Here I share an XGBoost model that delivers a 25% CAGR with minimal drawdown on Visa stock. In this free Substack post I share code and commentary for a powerful Machine Learning strategy that delivers powerful returns.

Have you tried to gguf the model? @ngxson has a fork for sesame in llamacpp

This is awesome!!

Does it support context length extension (eg YaRN)?

Wow

not familiar with this, curious about the incentive for TTS fine-tuning. (assume this is not doing voice cloning) Would a model with no emotion tags actually learn to handle <laugh> and <sigh> just from a fine-tune?

awesome ! 🔥 but whisper is a STT model not TTS this means unsloth also supports stt?

oh my 😦

🔥🔥

🚀


