gandolfxu

[TeleMelody] How to infer using pretained model

8

Can you provide a detailed description? I followed the README, but failed.

Can the model, ROC for example, generate such style score?

[ROC] Error when preparing data

1

python gen.py lmd_matched lmd_matched Traceback (most recent call last): File "gen.py", line 13, in from magenta_chord_recognition import infer_chords_for_sequence, _key_chord_distribution,\ ModuleNotFoundError: No module named 'magenta_chord_recognition'

[telemelody] Too many errors of template2melody when generating training data

3

Does it conforms to expectation? 

[meloform] process_lmd.py not found

1

The script for parsing LMD data is missing!

Training is too slow. WHY?

2

Two V100 GPU is used. But average gpu usage is about 30%。 2023-06-19 11:38:06,489 oprah_ms_istft_vits INFO ====> Epoch: 1 2023-06-19 11:39:16,343 oprah_ms_istft_vits INFO ====> Epoch: 2 2023-06-19 11:40:11,469 oprah_ms_istft_vits INFO...

could provide a example recipe?

12

1. Based on an open source dataset 2. Detailed training parameters

- Dataset: MAESTRO - Config: base_dataset_5.yaml. - add line 42: path: /root/dataset/maestro-v3.0.0/ - change: val_split: 0.02 - Command: - python train.py exp=base_dataset_5 trainer.gpus=1 90%|████████▉ | 4004/4463 [1:02:54

All audio files are in one fold. egs: "maestro" Disable wandb

how to generate longer audio sample?

1

egs: 3 minites