parler-tts
parler-tts copied to clipboard
Inference and training library for high-quality TTS models.
I've run through the steps to train a single voice, and it goes well until it comes time to actually **Fine-tuning Parler-TTS** step, i'm hitting a wall. It seems the...
Is there any way the Flash Attention 2 support for this model? if there is a way to do it i would love to get involved and help out! I've...
for the GPUPoor people
First of Kudos for such a brilliant project. I found a typo in the INFERENCE.md, that caused an issue. It referred to `device` rather than the `torch_device`.
congrats to release v2 parler-tts @sanchit-gandhi @ylacombe or anyone involve i am trying to explore reproduce multilinguality training, some question to ask if i want to train it multilingual 1....
Hi Congratulations on releasing the V1 update. I've integrated the v1 update into AllTalk v2 BETA https://github.com/erew123/alltalk_tts/tree/alltalkbeta If you are ever interested in making any updates to the setup for...
just want a list
Hey there. I'm trying to use `parler-tts` for near-realtime text to speech, just fast enough for conversations, on CPU inference. I'm trying to quantize your model in int8 using the...
I have tested the static cache inference, but the results are not as expected. I observed that the first two runs are for warming up, torch compiling... The third run...
At this [line](https://github.com/huggingface/parler-tts/blob/8b8c576e2dbdc29172e30be7d68fac9357cd92c5/parler_tts/modeling_parler_tts.py#L1430), a delay pattern mask is generated and applied to the initial audio IDs. Then, at this [line](https://github.com/huggingface/parler-tts/blob/8b8c576e2dbdc29172e30be7d68fac9357cd92c5/parler_tts/modeling_parler_tts.py#L1530), a mask is also generated to revert the delay on...