pheonis commented on issue mrq/ai-voice-cloning#370
No Module named Deepspeed> u can install it with > `pip install deepspeed==0.10.2` Hi mate, Tried to install but got this error instead! `Preparing metadata (setup.py) ... error error: subprocess-exited-with-error…
pheonis reopened issue mrq/ai-voice-cloning#370
No Module named Deepspeedpheonis opened issue mrq/ai-voice-cloning#370
Getting error starting ai voice cloningpheonis commented on issue mrq/ai-voice-cloning#225
Requesting tips to make inference as fast as possible> If you have a large dataset, go to your dataset and rename the audio folder so it doesnt get seen by the UI. Select 10-50 audio samples from the DS audio folder, put these in the voices folder…
pheonis commented on issue mrq/ai-voice-cloning#225
Requesting tips to make inference as fast as possible> Fine tune a model,~50-200 epochs. When training an american or british voice with a 10mins audio file(200 lines appx). How many epochs do you recommend? Whats the total loss and mel loss do…
pheonis commented on issue mrq/ai-voice-cloning#224
All finetuned models are unstable when synthesizing lengthy content> Not a solution, but might be a temporary "workaround": > > I've noticed that adding the line derimiter character as often as possible (after every period or comma), essentially turns your…
pheonis commented on issue mrq/ai-voice-cloning#223
Trying to Transcribe but getting error: 'Missing dataset: ./training/voice1//whisper.json'This thread might solve this https://git.ecker.tech/mrq/ai-voice-cloning/issues/177
pheonis opened issue mrq/ai-voice-cloning#224
All finetuned models are unstable when creting lengthy contentpheonis closed issue mrq/ai-voice-cloning#215
My newly baked model could only generate 3 seconds clipspheonis opened issue mrq/ai-voice-cloning#215
My newly baked model could only generate 3 seconds clipspheonis opened issue mrq/ai-voice-cloning#213
Amazing Suno-ai generates laugh,sigh and other expressionspheonis commented on issue mrq/ai-voice-cloning#198
Found some bad audio files during the middle of the training. What to do?``` Input #0, wav, from '/content/drive/MyDrive/ai-voice-cloning/training/new1test/audio/0.wav': Metadata: encoder : Lavf58.29.100 Duration: 00:00:01.92, bitrate: 256 kb/s Stream #0:0: Audio:…
pheonis commented on issue mrq/ai-voice-cloning#198
Found some bad audio files during the middle of the training. What to do?> and once all that's done create the folder structure for the dataset under training/ and copy over everything. I successfully managed to segment the audio file, created the train.txt file…
pheonis commented on issue mrq/ai-voice-cloning#198
Found some bad audio files during the middle of the training. What to do?> Semi-manually, I use `whisperx` to produce a timestamped transcription and then feed the timestamps into `ffmpeg` to cut things to size. -Okay. I tried to follow your method. Installed yt-dl,…
pheonis commented on issue mrq/ai-voice-cloning#198
Found some bad audio files during the middle of the training. What to do?How do you go about it? I read your comment in here [#133](https://git.ecker.tech/mrq/ai-voice-cloning/issues/133), You mentioned there that you proofread all the transcriptions and use smaller…
pheonis opened issue mrq/ai-voice-cloning#198
Found some audio files not good with some music in the middle of the training. What to do?pheonis commented on issue mrq/ai-voice-cloning#195
Having hardtime making Whispercpp and Whisperx work (COLAB)> > so, how would you install? right in the main ai-voice-cloning directory? > > I do `pip install git+https://github.com/m-bain/whisperx.git` in my home directory, but keep in mind I've never…
pheonis commented on issue mrq/ai-voice-cloning#195
Having hardtime making Whispercpp and Whisperx work (COLAB)>the different venv's conflict. I think the venv is not getting activated when executing setup_cuda.sh or start.sh. `"./venv/bin/activate: No such file or directory"` I can check in the…
pheonis commented on issue mrq/ai-voice-cloning#195
Having hardtime making Whispercpp and Whisperx work (COLAB)> I wouldn't clone them in a subdirectory of ai-voice-cloning just in case the different venv's conflict. so, how would you install? right in the main ai-voice-cloning directory?