Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
https://narilabs.com/blog/nari-labs-leads-coval-voice-ai-benchmarks/loading story #49701701
loading story #49701631
This is really cool work! I'm curious like what do you see as the biggest lever for speeding up TTS models or from a technical perspective that this was a promising direction in the first place to push on. If I were to guess, some distillation but I'm certain there are probably TTS model aware architectural changes that just make inference wayyyy faster?
> and Qwen3-ASR
Is the ASR inference engine open source as well?
loading story #49701647
{"deleted":true,"id":49699268,"parent":49699267,"time":1789402078,"type":"comment"}