Hi @zkx06111! 👋

This pull request adds an interactive web demo of the 2x upsampling checkpoint, based on your Colab notebook. You can try it out here: https://replicate.ai/zkx06111/wsrglow

Under the hood I've used an open source tool called Cog to build a Docker image, that is run by the Replicate servers. The Docker image can also be downloaded from the website for people who want to use WSRGlow from the command line without installing any Python dependencies.

If you click the "Sign in with GitHub" link you can edit the page and add more examples, and we'll feature your model on the Explore page.

In case you wonder who I am, I used to be a PhD student working on music source separation, and now I'm working on Replicate. I used to struggle to get baseline models working in my research, so we're building Cog and Replicate to make it easier to package trained models in a reproducible way. As part of that we're going around the internet making demos for our favorite models.

Google Colab and replicate.com virtual machines have a necessity of chunking 44kHz WAV stereo file into 53 seconds parts, otherwise it throws out of memory CUDA error.

I find it very comfortable to chunk WAVs using MKVToolnix which losslessly places WAV inside Matroska container. I kind of overcome the MKA issue by using MKVExtractGUI-2 with v.20 version of MKVToolnix (the only one compatible). I also used Lossless-Cut for pure WAVs, but it's more cumbersome and cannot really chunk a file every 53 seconds automatically. At least it has a merge option.

Hi, authors, Thank you for open sourcing this great repository.

I ran python train.py --config config.yaml, and got this error: FileNotFoundError: [Errno 2] No such file or directory: ''

Traceback (most recent call last):
  File "/home/wschoi/PycharmProjects/WSRGlow/train.py", line 345, in <module>
    WaveGlowTask4.start()
  File "/home/wschoi/PycharmProjects/WSRGlow/train.py", line 274, in start
    period=1 if hparams['save_ckpt'] else 100000
  File "/home/wschoi/PycharmProjects/WSRGlow/training_utils.py", line 23, in __init__
    os.makedirs(filepath, exist_ok=True)
  File "/home/wschoi/miniconda3/envs/wsrglow/lib/python3.7/os.py", line 223, in makedirs
    mkdir(name, mode)
FileNotFoundError: [Errno 2] No such file or directory: ''

Process finished with exit code 1

I guess this error was occurred because args_work_dir was set to '' unless args.exp_name is not a default value.

https://github.com/zkx06111/WSRGlow/blob/1b8fc4939c72b319efdb520ba2868eacf468ca18/hparams.py#L39-L42

and then, hparams_['work_dir'] is set to args_work_dir regardless of work_dir of config.yaml.

https://github.com/zkx06111/WSRGlow/blob/1b8fc4939c72b319efdb520ba2868eacf468ca18/hparams.py#L84-L86

TLDR;

This error is occurred only when args.exp_name == ''.

For those who want to quickly reproduce train.py I would recommend a script like below.

python train.py --config config.yaml --config config.yaml --exp_name WSRGlow

Hi I've been testing your model for a side project I'm working on. I'd like to take early historic recordings (1890-1920s), denoise & upsample them. I've already denoised them (amazingly so!), I'm trying to upsample using your model but it doesn't seem to be doing much. I used the code from the code lab and the config that's in the repo.

Is this not a good application of the model or did I do something incorrectly?

Here is the results I produced example_and_prediction_wav_files.zip

Spectrogram - Top is the example wav (Thomas Edison speaking 1912), bottom is the prediction. I can't hear a discernible difference and I'm well versed in audio engineering.

from infer import *

set_hparams(config='config.yaml')

model = WaveGlowMelHF(**hparams['waveglow_config']).cuda()

load_ckpt(model, 'model_ckpt_best.pt') model.eval()

fns = ['te_small.wav']

sigma = 1 for lr_fn in fns: lr, sr = load_wav(lr_fn) print(f'sampling rate (lr) = {sr}') print(f'lr.shape = {lr.shape}', flush=True) with torch.no_grad(): pred = run(model, lr, sigma=sigma) print(lr.shape, pred.shape) pred_fn = f'pred_{lr_fn}' print(f'sampling rate = {sr * 2}') sf.write(open(pred_fn, 'wb'), pred, sr * 2)

Hello, I'm trying to run your code. I just ran train.py with commands in readme, (with additional argument --hparams work_dir=ccc). But faced this error.

File "train.py", line 143, in training_step log_outputs = utils.tensors_to_scalars(log_outputs) AttributeError: module 'utils' has no attribute 'tensors_to_scalars'

I looked over commit logs, but utils.py never had that function.

Hi! I tried your pretrained checkpoint in colab and got some extra values at the spectrogram in the first case and broken harmonics in the second case. First audio is 44100Hz real speech (converted to 24k and then upscaled to 48k). Second audio is the output of text-to-speech system (22050, upscaled to 44100)

I don't hear any noticeable difference in both audios, is this expected?

this is the spectrogram representation in Audacity. Upper one is before, bottom is after. Mel scale