Skip to main content

A fork of the official implementation of the Grad-TTS model.

Project description

Grad-TTS

A fork of the official implementation of the Grad-TTS model based on Diffusion Probabilistic Modelling. This fork cleans up the code to focus on easy installation and inference.

Installation

Inference

See grad_tts_cli.py for how to use the model for inference.

python grad_tts_cli.py \
    --file /PATH/TO/TEXT_FILE \
    --checkpoint /PATH/TO/GRAD_TTS_CHECKPOINT \
    --hifigan_checkpoint /PATH/TO/HIFIGAN_CHECKPOINT \
    --outdir /PATH/TO/OUTPUT_DIR

You can download Grad-TTS and HiFi-GAN checkpoints trained on LJSpeech.

References

  • HiFi-GAN model is used as vocoder, official github repository: link.
  • Monotonic Alignment Search algorithm is used for unsupervised duration modelling, official github repository: link.
  • Phonemization utilizes CMUdict, official github repository: link.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

grad_tts-0.0.4.tar.gz (1.1 MB view details)

Uploaded Source

Built Distributions

grad_tts-0.0.4-cp311-cp311-win_amd64.whl (1.0 MB view details)

Uploaded CPython 3.11 Windows x86-64

grad_tts-0.0.4-cp311-cp311-musllinux_1_1_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.11 musllinux: musl 1.1+ x86-64

grad_tts-0.0.4-cp311-cp311-musllinux_1_1_i686.whl (1.4 MB view details)

Uploaded CPython 3.11 musllinux: musl 1.1+ i686

grad_tts-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.11 manylinux: glibc 2.17+ x86-64

grad_tts-0.0.4-cp311-cp311-macosx_11_0_arm64.whl (999.1 kB view details)

Uploaded CPython 3.11 macOS 11.0+ ARM64

grad_tts-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl (1.0 MB view details)

Uploaded CPython 3.11 macOS 10.9+ x86-64

grad_tts-0.0.4-cp310-cp310-win_amd64.whl (1.0 MB view details)

Uploaded CPython 3.10 Windows x86-64

grad_tts-0.0.4-cp310-cp310-musllinux_1_1_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.10 musllinux: musl 1.1+ x86-64

grad_tts-0.0.4-cp310-cp310-musllinux_1_1_i686.whl (1.3 MB view details)

Uploaded CPython 3.10 musllinux: musl 1.1+ i686

grad_tts-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.17+ x86-64

grad_tts-0.0.4-cp310-cp310-macosx_11_0_arm64.whl (999.2 kB view details)

Uploaded CPython 3.10 macOS 11.0+ ARM64

grad_tts-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl (1.0 MB view details)

Uploaded CPython 3.10 macOS 10.9+ x86-64

grad_tts-0.0.4-cp39-cp39-win_amd64.whl (999.6 kB view details)

Uploaded CPython 3.9 Windows x86-64

grad_tts-0.0.4-cp39-cp39-musllinux_1_1_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.9 musllinux: musl 1.1+ x86-64

grad_tts-0.0.4-cp39-cp39-musllinux_1_1_i686.whl (1.3 MB view details)

Uploaded CPython 3.9 musllinux: musl 1.1+ i686

grad_tts-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.9 manylinux: glibc 2.17+ x86-64

grad_tts-0.0.4-cp39-cp39-macosx_11_0_arm64.whl (999.8 kB view details)

Uploaded CPython 3.9 macOS 11.0+ ARM64

grad_tts-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl (1.0 MB view details)

Uploaded CPython 3.9 macOS 10.9+ x86-64

grad_tts-0.0.4-cp38-cp38-win_amd64.whl (1.0 MB view details)

Uploaded CPython 3.8 Windows x86-64

grad_tts-0.0.4-cp38-cp38-musllinux_1_1_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.8 musllinux: musl 1.1+ x86-64

grad_tts-0.0.4-cp38-cp38-musllinux_1_1_i686.whl (1.3 MB view details)

Uploaded CPython 3.8 musllinux: musl 1.1+ i686

grad_tts-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.4 MB view details)

Uploaded CPython 3.8 manylinux: glibc 2.17+ x86-64

grad_tts-0.0.4-cp38-cp38-macosx_11_0_arm64.whl (999.9 kB view details)

Uploaded CPython 3.8 macOS 11.0+ ARM64

grad_tts-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl (1.0 MB view details)

Uploaded CPython 3.8 macOS 10.9+ x86-64

File details

Details for the file grad_tts-0.0.4.tar.gz.

File metadata

  • Download URL: grad_tts-0.0.4.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for grad_tts-0.0.4.tar.gz
Algorithm Hash digest
SHA256 af8fd8edcd7893d473fa7011d4be5616b6f531af61d9081a45c96639a5e07249
MD5 0d6fb14d639aba966c8c48ab1fbd7f0b
BLAKE2b-256 9f0fabe34f18d27992e9e1142e9f72412f69ff2eaaa1bb15569e61131c2d3168

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-win_amd64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 b8672840e1ac39ed30166e397b67b75a5f9cf5b67e41de4f3c9f37c0341496d3
MD5 c470d6a748f4ea521bdf319de3fcb89d
BLAKE2b-256 1f1c48a71b0a55f139c5706f5b95c1ca2f30697f85d4602487f224e7e35a3207

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-musllinux_1_1_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-musllinux_1_1_x86_64.whl
Algorithm Hash digest
SHA256 84b8627c72b032f3b1e90ef03224e8cd475ffa831b8650c983510bbe8a3bb68f
MD5 564c2dcc525e382c671a2bbf553664ab
BLAKE2b-256 81c29c8b97ad16985054b76476a6d0443640a50efa4f054d2f6d3d13383cff84

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-musllinux_1_1_i686.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-musllinux_1_1_i686.whl
Algorithm Hash digest
SHA256 1722d2f7caa8fe72b02c87f11db3b956b3ff9b81daab15b7094e2cb501d70264
MD5 797110d5a1fbe1d7d53c242a1a7611be
BLAKE2b-256 a83edd14510dd3bd691b9ee559f0cb23ffe4555a9f4294848610177619a88f1a

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 952ebc1cb3be635a88b38b0d3d0663f05020dac41959179e6dceb2215ad5bd21
MD5 9b56f76a640c1f4832bfdf49bf02460e
BLAKE2b-256 86c465cc5eb80ea9012e88209ca76a6b24f7421ea3380ddbd726698b696e2f04

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 dec93d6ba06553e9aa9c06d7f34fe9f8c4253cac72efdc258a9603feb60d3ea9
MD5 5876cf48f27104bf737b589498270a97
BLAKE2b-256 8fe23926f5df010eb59b6c0f731e8d99f7cb1cc2c6c7675983fd420ef29ab1f1

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 7fecea87fed9b9074c3fecacc29d57102bd74d5642fcae40f8b7f96591775dec
MD5 a362bb621e5d965d69a735f43831e8a9
BLAKE2b-256 2569f2ea5fc337d8639ffe6f660ed498e51574d44c7a3d6bceabe35d46e2204d

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 783a6e4d61c590d4e33e857cd8cbce568b03013538ccf4668be586480edb2f54
MD5 caf25158ba469e8f59edc84b706a825c
BLAKE2b-256 5cbfc034f5f5d0efe72fae205150cdff86835ba1a6240148f6189c714f354a55

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-musllinux_1_1_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-musllinux_1_1_x86_64.whl
Algorithm Hash digest
SHA256 59f861015674f7a7fb99eae5cfc3fc3ea97f081ef7701e165a1ad9f2a5216b9e
MD5 5d4f2c27d6ecc882c405017cffac58c5
BLAKE2b-256 ee119da5fd3b35750301d64231b9dff16194b1c53832dce5a1f6d1342498cac9

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-musllinux_1_1_i686.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-musllinux_1_1_i686.whl
Algorithm Hash digest
SHA256 0c3aff63d75466d4bfc59acb039ae96c01fb6cd157c9a6bd27daf7d9d253ccc9
MD5 f6dc92fafe8bce3123745bc6243b79e9
BLAKE2b-256 ad5ee9953f5edf6b53766b95955b459dd0b30b5d99297667bd42b1778e4ea09d

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 d9f9602af8cdd5cd305da70ae6b91cb49c3dcd790425258e0d6cb2ec5741476d
MD5 0f4fc111ab3011b8cbb3b93817aea405
BLAKE2b-256 e4b1e874c10c599a4291af00accb4204b70ea43fcfc1bf94f8b16acb433dfaf2

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 2dd01fe9b52b144ce9117711fa72f31fdd22387eebe4c44289628ad12370deb5
MD5 350f592ab9f9b45b5cd8fc8a5a45bd2e
BLAKE2b-256 3dde4a2cfd3a42e6a42ff70ba24869127225aec1eb1556ffa55fdca722ad6c3f

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 35232db8711efbeeb4a61b7c5907f13ebf60a8a51019717a0334d2a8e221f075
MD5 a4497766816411a61c6769a70539417a
BLAKE2b-256 92b520ca7427dfa8467d2c2f87732ab78201881804ef355f2f5478652c6cd0db

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-win_amd64.whl.

File metadata

  • Download URL: grad_tts-0.0.4-cp39-cp39-win_amd64.whl
  • Upload date:
  • Size: 999.6 kB
  • Tags: CPython 3.9, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 3281203ff7b5b2df4f9113ad0f7c0df018dbf1695b8fbb96de0643439b4acc97
MD5 c2736eeac2cb9a9c4660916db8aacee8
BLAKE2b-256 6d6b6755f321716c98be28f4c3504f30ee28eb68eedb51fa7cbb4f07aaa3178f

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-musllinux_1_1_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-musllinux_1_1_x86_64.whl
Algorithm Hash digest
SHA256 b96334cbd543096fb29b61820ecc80fac7b501830b1347458a8aa2ccb74550c4
MD5 87adf34cb32222ac7c16e38722346604
BLAKE2b-256 c226d418e1ff8b595914223bed37166fe6236b560f6e148325e80f509287ebc1

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-musllinux_1_1_i686.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-musllinux_1_1_i686.whl
Algorithm Hash digest
SHA256 798baab0cb43659b88b64a0a1637d8661803a8a078732ac4c2cf41bef822b269
MD5 677a25b962bc4be10c41b33cdd2af100
BLAKE2b-256 8cd832ffbda3bde4ad3876ddd688fb3dda76b48312ec7df884f15e288cd965ea

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 f69bc9392f708e3bbb8ad760db0ff597b88eefa10524683defa45172cc6f9f96
MD5 3dd745a9359181a4e70e93c41f4d6b8c
BLAKE2b-256 3323a5d5515633923fd8b56c8515006f1744ad2623f79090b8cebcfc9b61282d

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 9c81624a6ac21188c39cf5a6118730d08b366f82ef37f02b243b0af34634ca8b
MD5 a3ebc49211f1b3ce9005b50d7075ceb6
BLAKE2b-256 fe43779736b20a61f5df2249c7c5df71bf1d0da1a36d77cdabfd5ae9b1276e17

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 688b5816846fe196629cdc9b43c99bb087830c9aff813fcbddacec27919f34c3
MD5 9adc7f33507b9983fd69522ef46d34d1
BLAKE2b-256 582d08619c6964e00200d90cc859c8e3ab16cf559370e225516e2f8093fa37be

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-win_amd64.whl.

File metadata

  • Download URL: grad_tts-0.0.4-cp38-cp38-win_amd64.whl
  • Upload date:
  • Size: 1.0 MB
  • Tags: CPython 3.8, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 917afad0013a4baa70ca326b008257886838d850f79cfea222068575e4baab7c
MD5 460412a39207dc62c73e7e0d2e1be262
BLAKE2b-256 a56ca0fed53a42a1ecdabfdb7df7e7340a8907b7594d8b0ec19e7aa23fcd3cb4

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-musllinux_1_1_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-musllinux_1_1_x86_64.whl
Algorithm Hash digest
SHA256 480127d5741dbf2ed3e188ec6d5a11d8492f8b9c22bb73cffe2039acecd7f73c
MD5 584cff1d990cbce91f795af3783d7852
BLAKE2b-256 ae1d31610231ee25728a98be6a45930501aa83d53c4c29b6031928845ea61a48

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-musllinux_1_1_i686.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-musllinux_1_1_i686.whl
Algorithm Hash digest
SHA256 e922a99d147b7e4b87684ab50cd2115ff61ac9b999702bcb2b5e9cba9c12164c
MD5 34e06603637b7bc1e55f97298916006e
BLAKE2b-256 99cf279b5039607a296b3583d2c678789c2da08f65fa2fc3a7c32b0d6e2fe39e

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 0b639a13e32b90759ed313e7f1b1a4f90f3cfcc119ec016e3ddac69a9bd402d6
MD5 fd85ff631d4580d070a9142ffa527d8a
BLAKE2b-256 2a0a68db542fd2c5dd2c450c7c1917f50bb4ea7c7067e4ff60fea8426225f9a3

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 22950fdf5c1bc747d7d44d99dddc154a88cb010547f670a76428e2ff28464c80
MD5 667ce187bf4a0a6c072be13f98ff82b3
BLAKE2b-256 42c63540a8f94ed8b60c24a93d66c9bbc2ea2a19adfc55941620889d1c802199

See more details on using hashes here.

File details

Details for the file grad_tts-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for grad_tts-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 fa1f2b069a7b7dcaccc02a214a6c06273462273b494520719865904699cddca3
MD5 dd4d5d53a3097db4eeac8d01ce0b9508
BLAKE2b-256 ec7dc145df480ba16a18fd67eb7c7b9bab342cf797d400692d0ed1d32e8fd190

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page