akshay4malik

I am doing it for Hindi Language. We have trimmed silences from the beginning and end of the audio files.

Yes, We were getting good results on Tacotron 2 with the same data. But flowtron offers several new features, so we thought of training on it as well.

Ok, I will try that and will post the response. But what can be the possible reason in case I am directly trying to train flowtron model.

While training from pretrained Tacotron2 model, there are some issues. I have tried to overcome some of them, But there are properties of Tacotron2 model, which are causing problems. Here...

Yes I am using warmstart_checkpoint_path, and I have changed "include_layers": ["speaker", "encoder", "embedding"] to "include_layers": ["encoder", "embedding"] and using n_flows = 1. As you mentioned these errors are harmless, how...

No, the problem in that function occurs [here](https://github.com/NVIDIA/flowtron/blob/edae4309632f291f8c0ab6f823e280467f2829ff/train.py#L96) But this can be solved by removing this if condition as there are no speaker embeddings in Tacotron2 model. The problem occurs...

I have not added checkpoint_path, below is the config json `"train_config": { "output_directory": "outdir", "epochs": 10000000, "learning_rate": 1e-4, "weight_decay": 1e-6, "sigma": 1.0, "iters_per_checkpoint": 5000, "batch_size": 1, "seed": 1234, "checkpoint_path": "",...

I got it, I am sorry, I am a little mistake while giving the "train" command. Just when you pointed it out, I looked at the functions. The training has...

> Does it work when you comment out [this](https://github.com/NVIDIA/flowtron/blob/edae4309632f291f8c0ab6f823e280467f2829ff/train.py#L96-97) and pass a model to `warmstart_checkpoint_path`? The error was coming because while running the code, I was giving the checkpoint path....

> Great! Let us know once you're able to train with the male hindi voice. Sure, I will inform you for sure. But here is something things that I would...