logan hart

[email protected]

@airtimemedia Earth doing Deep Learning

Results 19 comments of


                                            logan hart

[Bug] The model does not train with the new hyperparameters given by command line when trying to restart a training with `restore_path` and `continue_path`

> Hi @Ca-ressemble-a-du-fake, Thanks again for your quick response. > > I have structured the data so that each speaker has its own metadata and folder. Therefore, I am treating...

[Bug] The model does not train with the new hyperparameters given by command line when trying to restart a training with `restore_path` and `continue_path`

> Good morning @Ca-ressemble-a-du-fake, > I tried to use train_tts.py and now I have another error related to the own data. I've been trying to see where the error comes...

[Bug] The model does not train with the new hyperparameters given by command line when trying to restart a training with `restore_path` and `continue_path`

> Hi @loganhart420 I am the colleague of @GerrySant. In the end we restructured our data in `vctk_old` format and launched some processes using the `train_tts.py`, and we still have...

[Feature request] VRAM calculated + precaution warning message

> **Calculate the amount of vram[GPU memory] will be used in the first stage of trainer.fit** > > Based on the batch size, dataset, and other variables. Sometimes it takes...

Delightful TTS implementation

> Does it avaiable for now I'm currently training the pretrained models, the pr to follow along is here: https://github.com/coqui-ai/TTS/pull/2095

[Bug] Wrong number of warmup steps in recipes with default Trainer.scheduler_after_epoch=True

@vanIvan Can you try again on the latest version?

Delightful TTS implementation

> Polish is awesome! > When would it be ready? Can I download the model even if its WIP ? you can clone the branch right now and train from...

[Bug] Multiple speaker requests?

I was able to do successfully generate audio using both a list of strings with length of 1 and 2. ``` from TTS.api import TTS tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True) tts.tts_to_file(...

[Bug] Fine-error in trainer

I wasn't able to replicate using the same env. maybe the version of the trainer is mismatched. Try installing the newest version of TTS.

[Bug] The model does not train with the new hyperparameters given by command line when trying to restart a training with `restore_path` and `continue_path`

> Hey @loganhart420, have you discovered anything else? The behavior is the same if the changes are made directly in the config. I haven't yet. I'm exploring this all morning...

1
2
›