Open
Conversation
blisc
reviewed
Nov 4, 2022
tts-evaluation-MCD-DTW.ipynb
Outdated
| "## Conclusion\n", | ||
| "<img src=\"imgs/riva-tts-MCD_DTW_final_comparision.jpeg\">\n", | ||
| "\n", | ||
| "From the graph above the value of MCD is greater for radtts audios than radtts audios, this is also reflected in the average MCD value for both models. Therefore we can conclude that fastpitch has better convergence than radtts. However we cannot evaluate the quality of audios generated by these models using MCD. MCD is a great tool for testing model convergence, but generated audios may have pronunciation and quality artefacts. Therefore MCD evaluation should be followed by a MOS(Mean opinion score) and CMOS(Comparative mean opinion scores) evaluation." |
Collaborator
There was a problem hiding this comment.
Can you clarify this sentence?
blisc
reviewed
Nov 8, 2022
tts-evaluation-MCD-DTW.ipynb
Outdated
| "sr = 22050\n", | ||
| "\n", | ||
| "## Mfcc params\n", | ||
| "n_mfcc=n_mels" |
tts-evaluation-MCD-DTW.ipynb
Outdated
| "source": [ | ||
| "def mel2mfcc(mels):\n", | ||
| " mfcc = librosa.feature.mfcc(S=mels, n_mfcc=n_mfcc)\n", | ||
| " mfcc = librosa.power_to_db(mfcc, ref=np.max)\n", |
| @@ -0,0 +1,495 @@ | |||
| { | |||
Collaborator
There was a problem hiding this comment.
How did you get the mel spectrograms from the models?
Contributor
Author
There was a problem hiding this comment.
For radTTS I used: https://github.com/NVIDIA/radtts
For fastpitch, I used the method described here: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/tts_en_fastpitch
Collaborator
There was a problem hiding this comment.
Do have a code snippet that you can add to the notebook?
Contributor
Author
There was a problem hiding this comment.
I can add for fastpitch, for radTTS I had to do some changes in their inference script. That wont be possible in the notebook.
3 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Mcd tutorial