Article 34 From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages
Decider Audio Spoken and audio-only benchmarks to test whether audio decision models hear more than the words. SebastianBodza/decider-audio-banking77 Viewer • Updated 6 days ago • 13.1k • 19 SebastianBodza/decider-audio-clinc150 Viewer • Updated 6 days ago • 23.7k • 18 SebastianBodza/decider-audio-when2call Viewer • Updated 6 days ago • 12.6k • 20 SebastianBodza/decider-audio-anli Viewer • Updated 2 days ago • 186k • 100
Decider Audio Spoken and audio-only benchmarks to test whether audio decision models hear more than the words. SebastianBodza/decider-audio-banking77 Viewer • Updated 6 days ago • 13.1k • 19 SebastianBodza/decider-audio-clinc150 Viewer • Updated 6 days ago • 23.7k • 18 SebastianBodza/decider-audio-when2call Viewer • Updated 6 days ago • 12.6k • 20 SebastianBodza/decider-audio-anli Viewer • Updated 2 days ago • 186k • 100
Running on Zero Agents 11 Kartoffel-TTS (Based on Chatterbox) - German Text-to-Speech Demo 📢 Expressive Zeroshot TTS
Running on Zero Agents 32 Kartoffel-TTS (Based on Chatterbox) - German Text-to-Speech Demo 📢 Expressive Zeroshot TTS
Build error Agents 1 SmolKartoffel-135M-v0.1 🔥 German zero Shot voice cloning with llasa 1b finetuned
Runtime error Agents 11 Kartoffel-1B-v0.1-Llasa 1b Tts 🔥 German zero Shot voice cloning with llasa 1b finetuned
SebastianBodza/Kartoffel_Orpheus-3B_german_synthetic-v0.1 Text-to-Speech • 3B • Updated May 17, 2025 • 139 • 11
SebastianBodza/Kartoffel_Orpheus-3B_german_natural-v0.1 Text-to-Speech • 3B • Updated May 17, 2025 • 700 • 23