Code

Adding OverFlow#2183

Code

Merged

erogol merged 32 commits intocoqui-ai:devcoqui-ai/TTS:devfrom shivammehta25:devshivammehta25/TTS:devCopy head branch name to clipboardDec 12, 2022

+2,223-4

Commits

Commits on Nov 26, 2022

• Adding encoder

  shivammehta25

  committed
  405bffe

  Copy full SHA for 405bffe

Commits on Nov 27, 2022

• currently modifying hmm

  shivammehta25

  committed
  d607993

  Copy full SHA for d607993

Commits on Nov 28, 2022

• Adding hmm

  shivammehta25

  committed
  a324920

  Copy full SHA for a324920

Commits on Nov 30, 2022

• Adding overflow

  shivammehta25

  committed
  8628648

  Copy full SHA for 8628648

Commits on Dec 1, 2022

• Adding overflow setting up flat start

  shivammehta25

  committed
  6ec83c4

  Copy full SHA for 6ec83c4

• Removing runs

  shivammehta25

  committed
  783a982

  Copy full SHA for 783a982

• adding normalization parameters

  shivammehta25

  committed
  10f15e0

  Copy full SHA for 10f15e0

• Fixing models on same device

  shivammehta25

  committed
  aff8b1f

  Copy full SHA for aff8b1f

Commits on Dec 2, 2022

• Training overflow and plotting evaluations

  shivammehta25

  committed
  62941d6

  Copy full SHA for 62941d6

Commits on Dec 3, 2022

• Adding inference

  shivammehta25

  committed
  f448ea4

  Copy full SHA for f448ea4

Commits on Dec 4, 2022

• At the end of epoch the test sentences are coming on cpu instead of gpu

  shivammehta25

  committed
  ff33837

  Copy full SHA for ff33837

Commits on Dec 5, 2022

• Adding figures from model during training to monitor

  shivammehta25

  committed
  3edb0d2

  Copy full SHA for 3edb0d2

• reverting tacotron2 training recipe

  shivammehta25

  committed
  5fc800c

  Copy full SHA for 5fc800c

• fixing inference on gpu for test sentences on config

  shivammehta25

  committed
  427dfe5

  Copy full SHA for 427dfe5

• moving helpers and texts within overflows source code

  shivammehta25

  committed
  ecc12c6

  Copy full SHA for ecc12c6

• renaming to overflow

  shivammehta25

  committed
  b86f3f8

  Copy full SHA for b86f3f8

• moving loss to the model file

  shivammehta25

  committed
  995ee93

  Copy full SHA for 995ee93

• Fixing the rename

  shivammehta25

  committed
  5b0fe46

  Copy full SHA for 5b0fe46

• Model training but not plotting the test config sentences's audios

  shivammehta25

  committed
  5377f87

  Copy full SHA for 5377f87

• Formatting logs

  shivammehta25

  committed
  bd5be6c

  Copy full SHA for bd5be6c

• Changing model name to camelcase

  shivammehta25

  committed
  755aa6f

  Copy full SHA for 755aa6f

• Fixing test log

  shivammehta25

  committed
  1350a4b

  Copy full SHA for 1350a4b

Commits on Dec 6, 2022

• Fixing plotting bug

  shivammehta25

  committed
  3c986fd

  Copy full SHA for 3c986fd

• Adding some tests

  shivammehta25

  committed
  4a5b1a0

  Copy full SHA for 4a5b1a0

Commits on Dec 7, 2022

• Merge branch 'coqui-ai:dev' into dev

  shivammehta25

  authored
  5b1dabc

  Copy full SHA for 5b1dabc

Commits on Dec 8, 2022

• Adding more tests to overflow

  shivammehta25

  committed
  f43d7e3

  Copy full SHA for f43d7e3

Commits on Dec 9, 2022

• Adding all tests for overflow

  shivammehta25

  committed
  c3d0167

  Copy full SHA for c3d0167

• making changes to camel case in config

  shivammehta25

  committed
  ddefe34

  Copy full SHA for ddefe34

Commits on Dec 10, 2022

• Adding information about parameters and docstring

  shivammehta25

  committed
  c2df9f3

  Copy full SHA for c2df9f3

• removing compute_mel_statistics moved statistic computation to the model instead

  shivammehta25

  committed
  9927434

  Copy full SHA for 9927434

• Added overflow in readme

  shivammehta25

  committed
  340cd0b

  Copy full SHA for 340cd0b

Commits on Dec 11, 2022

• Adding more test cases, now it doesn't saves transition_p like tensor and can be dumped as json

  shivammehta25

  committed
  aca3fe1

  Copy full SHA for aca3fe1