shreeshailgan

In `Section 3.1`, under `Model Configuration`, the paper states that the decoder consists of 4 FFT Transformer blocks. However, the provided checkpoints (and the `model.yaml` configs) have 6 FFT Transformer...

Hey @ming024, Could you specify the MFA version you used to generate the textgrids you have provided in your repo? Also, did you generate those textgrids by just aligning using...

MFA Validate Inconsistent Output

2

I am running `mfa validate` on the LibriTTS-train-clean-460 dataset using an IPA dictionary I have. The output contains: ``` WARNING 288196total OOV tokens ``` However, in the generated `oov_counts.txt` file...

Doubt in CE-RVQ loss when training NaturalSpeech 2

5

When training the NS2 model, for calculating the CE-RVQ loss, we have the `diff_ce_loss` method: https://github.com/open-mmlab/Amphion/blob/d33551476d792e608c13cec1bfa32283c868a2fb/models/tts/naturalspeech2/ns2_loss.py#L65 This function takes the ground truth indices `gt_indices` and the predicted distribution `pred_dist` For...