Akash Gupta
Akash Gupta
I use the rpi pico to request telemetry over uart and it seems to be working well as documented in this [repo](https://github.com/Guppy16/pico-dshot/tree/onewire-telem). Is auto-telemetry the same as [onewire KISS ESC...
https://github.com/huggingface/parler-tts/pull/110 Does this help? I have a notebook demonstrating how to try and maintain voice consistency.
Did this work for you, @elricwan ?
Please see my attempt at alleviating this issue in this PR: https://github.com/huggingface/parler-tts/pull/110 The idea is to try and "prefix" the TTS with some audio to get it to mimick the...
Perhaps the bugfixes also need to be applied in `ParlerTTSForCausalLM`? (I haven't touched this class so I'm not sure about it's intended use)
@ylacombe Would it be possible for you to review this?
Thanks a lot for reviewing this, as well as your great suggestions! I'll work on this in the coming few days.
> 2. I'd rather have an issue opened that explain how to do your voice enrolment thing than a notebook ! Would you like to write a guide about this...
https://github.com/huggingface/parler-tts/pull/110 Does this help? I have an example notebook doing continuation as well. You need to use the `decode_input_ids` argument (as well as fix a bug similar to how @stg1205...
Perhaps u can also experiment with the `min_new_tokens` parameter. I believe in ParlerTTS, a single audio token represents ~12 ms of audio, so if you want to generate 20 secs,...