Aaron Jorgensen comments

Results 18 comments of


                                            Aaron Jorgensen

The denoising effect is abnormal

retrained and get same results. I wonder if it needs different noise generation? What do you suggest?

Error with 'cloning_reference_wav'

Removing it seems to have worked.

Will switching to SeamlessM4Tv2 be better

maybe MeloTTS/OpenVoice would be a good replacement, also distil_whisper

example using microphone

if it helps, here is a quick FastAPI implementation I just did ```from fastapi import FastAPI, File, UploadFile, HTTPException from pydantic import BaseModel import torch from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor,...

Question: what's the logic reason of 2GB file size limit? Is it possible to bypass this limit?

my guess would be in order to keep under the timeout limit for lambdas.

openai.OpenAIError

nothing works, I even did another fresh install. It seems like the config variables are being completely ignored.

No module named 'mmcv._ext' 怎么解决

I solved it by building from source

[Feature Request]: Add support of GLM models from Z.ai

I just implemented this and am testing it now. If you like I can share the link once working