Not sure where or how to properly submit a ticket for the colab creators, but, the colab has been broken for weeks now. I check every couple days and it's only getting worse, stopping with errors sooner and sooner in the process.
I’m currently working on a fixed colab version, I’ll give you a heads up if I get it working Seems that we need to force downgrade all the packages that were changed in recent google colab updates
Does the colab notebook no longer work? I get this error in the first cell block: ERROR: pip's legacy dependency resolver does not consider dependency conflicts when selecting packages. This behaviour is the source of the following dependency conflicts. albucore 0.0.14 requires numpy>=1.24, but you'll have numpy 1.22.0 which is incompatible.
I have a fine tuned model and i downloaded it in my pc. i want to run this fine tuned model on my pc and implement it to a web or mobile application? Do you know how do i achieve this?
I gave up on it, i tried to train it on a 2:30 duration audio that was cleaned properly and it just was still training after 20 minutes on the default settings
I fine tuned the model and saved it in my device . but in every time I want to use the model I should provide the speaker_wav which is from data used for fine tuning and this process(analyses the record) take a long time. so, how can I use the model with my own speaker id to avoid providing it the speaker wav ???
This might sound like a dumb question, but how would you load the fine tuned model in other python programs. I know we get a config.json, vocab.json and a modal.pth files after the fine tuning process, but would we use the TTS.api?
Also, it doesn't seem to run locally after downloading the model.pth, vocab.json and config.json Do you need to download the whisper model for it to work locally or is that just for training? Edit: No the whisper model didn't change it, I was desperate, figured maybe it needed to check you had requirements for training in order to inferencing or something, that that didn't do it. Removing the quotation makes from the paths made it look like it was loading for a moment, but then after 4 seconds it just says "error." When loading the finetuned model.
@@Gobolinn disappointing. i've been looking for a good ja->en voice clone tts. best I've found so far is moegoe which ends up being a bit weird sounding with the pacing when doing inference in english (but the sound of the voice is spot on). Every other voice clone thing I've tried doesn't seem to match the voice at all. I was hoping this would work but it seems not?
I love the Coqui performance, results and ease of use, but Is it possible to be even easier? Like 1 file for input file for training or microphone input, button 2 for training, and 3 type and speak. I am not sure why in year 2024 we still need to copy and paste text ...
This is currently the peak of technology. The top of tech available to the public. It's the very first iteration of the ui too. So in the future it might get easier, the more people want to use it. Like automatic1111s ui used to be barebones and hard to use. But now it's become a lot more user friendly. Just a few months ago all this was pure command line
Maybe you just found out about it😄 People are already making money from the same peak technology. I paid months ago for this type of peak technology and moths in the age of AI means long time ago :)
@@HyperUpscale Perhaps I should have clarified myself more. I meant the peak open source versions, that are accessable for everyone for free. If you take the older models of coqui for example, just a few months ago it would have taken you many hours to train a proper model that works well on any ways. A year ago even just a basic voice was considered a big step towards open source AI technology. I am well aware of AI-Voices being used for many many years now, however, technology of this caliber were not yet accessable to the everyday user for free, only through paid alternatives.
when I ran the cell 1,I got this error message Building wheel for docopt (setup.py) ... done ERROR: pip's legacy dependency resolver does not consider dependency conflicts when selecting packages. This behaviour is the source of the following dependency conflicts. lida 0.0.10 requires fastapi, which is not installed. lida 0.0.10 requires kaleido, which is not installed. lida 0.0.10 requires python-multipart, which is not installed. lida 0.0.10 requires uvicorn, which is not installed. librosa 0.10.1 requires numpy!=1.22.0,!=1.22.1,!=1.22.2,>=1.20.3, but you'll have numpy 1.22.0 which is incompatible. plotnine 0.12.4 requires numpy>=1.23.0, but you'll have numpy 1.22.0 which is incompatible. pywavelets 1.5.0 requires numpy=1.22.4, but you'll have numpy 1.22.0 which is incompatible. tensorflow 2.15.0 requires numpy=1.23.5, but you'll have numpy 1.22.0 which is incompatible. gruut 2.2.3 requires networkx=2.5.0, but you'll have networkx 3.2.1 which is incompatible.
Not sure where or how to properly submit a ticket for the colab creators, but, the colab has been broken for weeks now. I check every couple days and it's only getting worse, stopping with errors sooner and sooner in the process.
I’m currently working on a fixed colab version, I’ll give you a heads up if I get it working
Seems that we need to force downgrade all the packages that were changed in recent google colab updates
Fixed
colab.research.google.com/drive/1sqQqzupo2pdjgggkrbM60sU6sBFYo3su?usp=sharing
@@drewthomasson949 Sweet! Glad to hear it. And, thanks in advance for all the hard work! :)
Fixed
colab.research.google.com/drive/1sqQqzupo2pdjgggkrbM60sU6sBFYo3su?usp=sharing
@@drewthomasson949 Can you please share the colab? I can't run the second cell, it gives a bunch of errors
"ImportError: tokenizers>=0.19,
Is there an example of a narration script that produces the best cloning results? Perhaps one that includes all the phonemes?
Does the colab notebook no longer work? I get this error in the first cell block:
ERROR: pip's legacy dependency resolver does not consider dependency conflicts when selecting packages. This behaviour is the source of the following dependency conflicts.
albucore 0.0.14 requires numpy>=1.24, but you'll have numpy 1.22.0 which is incompatible.
clone the git repo. fix version and it will run
@@HimanshuSingh-j1r5n can you tell me how to do it please?
it would be amazing to know how to load the model in a local enviroment now that i´ve train it
any idea on this? Ive got the fine tuned model and the json files, where do I load it for future use?
Download the model. You can transfer into your google drive lol. If you could not this video would have 0 sense@@sayedyasser2
is there are any options for fine-tuning much longer eg: a few hours for better results?
Great video, once saved the model, can we make inference locally using the tts module?
I have a fine tuned model and i downloaded it in my pc. i want to run this fine tuned model on my pc and implement it to a web or mobile application? Do you know how do i achieve this?
It seems to work really nicely. But how can I run the model in coqui? E.g. using the python api or the tts server?
Me too.
for api, replace the files in your computer with the files you've downloaded@@YevgeniyChannel
Do I have to start again from the beginning if I want more epochs?
I want Prompt To Voice please.
Do you know how hard it is to find a voice according to my specifications?
I gave up on it, i tried to train it on a 2:30 duration audio that was cleaned properly and it just was still training after 20 minutes on the default settings
fine-tuning takes time. You need to wait for a bit.
depends it takes around 5 min for with 10min audio for fine tuning. Just make sure you use T4 GPU@@erogol
@@torusx8564 got kicked out by google due to some error about free limits sadly.
I fine tuned the model and saved it in my device . but in every time I want to use the model I should provide the speaker_wav which is from data used for fine tuning and this process(analyses the record) take a long time. so, how can I use the model with my own speaker id to avoid providing it the speaker wav ???
Great notebook & video !
Unfortunate, it seems notebook gradio not support Thai yet.
Could you please also guide me how to do it in another language ?
Is this Fine Tuning for XTTS v1 or v2?
This might sound like a dumb question, but how would you load the fine tuned model in other python programs. I know we get a config.json, vocab.json and a modal.pth files after the fine tuning process, but would we use the TTS.api?
Guys, I repeated your lesson, but in the files of all CMS models wherever I see, there is an index file / how to create it or is it not needed???))))
? wdym
Also, it doesn't seem to run locally after downloading the model.pth, vocab.json and config.json
Do you need to download the whisper model for it to work locally or is that just for training?
Edit: No the whisper model didn't change it, I was desperate, figured maybe it needed to check you had requirements for training in order to inferencing or something, that that didn't do it. Removing the quotation makes from the paths made it look like it was loading for a moment, but then after 4 seconds it just says "error." When loading the finetuned model.
prob just drop those files over the xtts model you have installed locally.
clone the git repo. fix version and it will run.
How to download that XTTS program??
clone the git repo. fix version and it will run
Very very cool!!!! Doesn't work when dataset language is set to ja on 1st tab though - doesn't seem to be able to populate the metadata_eval.csv
encountered the same issue looks like ja isnt supported yet
@@Gobolinn disappointing. i've been looking for a good ja->en voice clone tts. best I've found so far is moegoe which ends up being a bit weird sounding with the pacing when doing inference in english (but the sound of the voice is spot on). Every other voice clone thing I've tried doesn't seem to match the voice at all. I was hoping this would work but it seems not?
Got kicked out by google due to free tier limits..
company shutdown?
I love the Coqui performance, results and ease of use, but Is it possible to be even easier? Like 1 file for input file for training or microphone input, button 2 for training, and 3 type and speak.
I am not sure why in year 2024 we still need to copy and paste text ...
The thing you are looking at is not meant for end-users, it's for developers.
This is currently the peak of technology. The top of tech available to the public. It's the very first iteration of the ui too. So in the future it might get easier, the more people want to use it.
Like automatic1111s ui used to be barebones and hard to use. But now it's become a lot more user friendly.
Just a few months ago all this was pure command line
Maybe you just found out about it😄
People are already making money from the same peak technology.
I paid months ago for this type of peak technology and moths in the age of AI means long time ago :)
@@HyperUpscale Perhaps I should have clarified myself more. I meant the peak open source versions, that are accessable for everyone for free. If you take the older models of coqui for example, just a few months ago it would have taken you many hours to train a proper model that works well on any ways. A year ago even just a basic voice was considered a big step towards open source AI technology. I am well aware of AI-Voices being used for many many years now, however, technology of this caliber were not yet accessable to the everyday user for free, only through paid alternatives.
👍@@BlenderBeanie
Shoutout Two Minute Papers i guess :D
Not working sir make a new tutorial
I need help please
lol on what
To make effects and AI voices @@torusx8564
Deron Dam
Davin Crest
when I ran the cell 1,I got this error message
Building wheel for docopt (setup.py) ... done
ERROR: pip's legacy dependency resolver does not consider dependency conflicts when selecting packages. This behaviour is the source of the following dependency conflicts.
lida 0.0.10 requires fastapi, which is not installed.
lida 0.0.10 requires kaleido, which is not installed.
lida 0.0.10 requires python-multipart, which is not installed.
lida 0.0.10 requires uvicorn, which is not installed.
librosa 0.10.1 requires numpy!=1.22.0,!=1.22.1,!=1.22.2,>=1.20.3, but you'll have numpy 1.22.0 which is incompatible.
plotnine 0.12.4 requires numpy>=1.23.0, but you'll have numpy 1.22.0 which is incompatible.
pywavelets 1.5.0 requires numpy=1.22.4, but you'll have numpy 1.22.0 which is incompatible.
tensorflow 2.15.0 requires numpy=1.23.5, but you'll have numpy 1.22.0 which is incompatible.
gruut 2.2.3 requires networkx=2.5.0, but you'll have networkx 3.2.1 which is incompatible.
Kessler Mountain
Gislason Brook
Simonis Walk
Alfreda Station
Alejandrin Parkways
Bashirian Garden
Armstrong Mount
Nicola Tunnel
Bethany Mill
Tess Street
Cremin Wells
Klein Hills
Jamel Motorway
you are a good girl, thanks coqui
Kub Squares
Walker Angela Lewis Brian Williams Deborah
Allen Richard Harris Frank Johnson Deborah
Feil Fords
)))
Moore Susan Allen Joseph Jackson Daniel
If your notebook is broken, run '!pip install fastapi==0.111.0' after installations. It fixes it. Like the comment to show love.
lol share a link to your working colab plz idk which colab your referring to anyway theres multiple.
Also get a pip freeze of the working env so none of us have to run into this anymore lol
amazing @coqui