Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Alternative title: Text to speech in 9.36M, English only.by mcbetz
- Amazing quality for small size, but definitely not that enjoyable to listen to.
IMHO, its at about the same quality level of historic TTS tools.
by itake - I'm not sure which historic tools you mean, but to me this sounds much better than anything older than ten years ago.by stavros
- I think we need more neurons in the human brain than parameters in this model for speech. I wonder what it says about the human brain vs LLM efficiency.by da-x
- amazing quality for such small size!by jsomedon
- I'd love to hear it but it seems your quota is exhausted.by StilesCrisis
- wrote a web-demo, runs in your browserby g58892881
- this is extremely encouraging for individuals/small companies being able to train pareto-frontier TTS models (specifically compute required to run vs quality of model output)by sudb
- How heavy in inference on this? The model would easily fit on many microcontroller modules, I wonder if they could run it?by K0balt
- I keep seeing tts stories here. Is it just an interesting subset of the llm world, or is there a huge use case I’m somehow missing?by billdueber
- I use STT/TTS to interface with a local LLM for Home Assistant in my house.
- I just built my own voice assistant with my Pebble Time 2 watch and it uses a VPS hosted TTS (Piper) and Hermes agent.
I learned about all of these projects on HN at one point or another.
by SamPatt - The inflections are weird but this doesn't sound like a robot. Not bad!by NetOpWibby
- This is impressive. I wish there were a voice clone option.by tmaly
- With so few parameters, I imagine a voice fine-tune might be readily tractable.by fastball
- Couple highlights:
> Complete local text-to-waveform speech synthesis under 10M parameters.
In case, like me, you hoped "complete" voice might mean both stt and tts. Not to speak poorly of it, just clarifying.
> English only, with one fixed male voice. This is not zero-shot voice cloning.
(And then a bunch of statements on limitations that I read as 'quality can be spotty but if you play with it it should be fine') But like. In <10M params I'm not judging:)
by yjftsjthsd-h - When would “text-to-waveform speech synthesis” ever imply speech to text?by semiquaver
- This is amazing, the quality blow my mind for such small model! I just replaced my old onnx model with yours!
here my implementation with speech dispatcher and server: https://github.com/skorotkiewicz/inflect-speechd
thanks for shearing!
by modinfo