Rendered at 17:06:48 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
yjftsjthsd-h 14 hours ago [-]
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:)
semiquaver 34 minutes ago [-]
When would “text-to-waveform speech synthesis” ever imply speech to text?
modinfo 11 hours ago [-]
This is amazing, the quality blow my mind for such small model! I just replaced my old onnx model with yours!
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)
billdueber 3 hours ago [-]
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?
eightysixfour 2 hours ago [-]
I use STT/TTS to interface with a local LLM for Home Assistant in my house.
NetOpWibby 9 hours ago [-]
The inflections are weird but this doesn't sound like a robot. Not bad!
tmaly 15 hours ago [-]
This is impressive. I wish there were a voice clone option.
fastball 13 hours ago [-]
With so few parameters, I imagine a voice fine-tune might be readily tractable.
13 hours ago [-]
phoenixranger 44 minutes ago [-]
amazing! was looking for something similar
StilesCrisis 4 hours ago [-]
I'd love to hear it but it seems your quota is exhausted.
> 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:)
here my implementation with speech dispatcher and server: https://github.com/skorotkiewicz/inflect-speechd
thanks for shearing!
https://inflect-tts.geronimo-labs.com
code: https://github.com/geronimi73/inflect-tts
On my iPhone 14 Pro the page crashes after 2-3 plays. I wonder if it uses too much memory?
IMHO, its at about the same quality level of historic TTS tools.