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

These details have not been verified by PyPI

Project links

Homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

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

These details have not been verified by PyPI

Project links

Homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

This version

0.0.4

Aug 25, 2023

0.0.3

Aug 21, 2023

0.0.2

Aug 18, 2023

0.0.1

Aug 18, 2023

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 hashes)

Uploaded Aug 25, 2023 Source

Built Distributions

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

Uploaded Aug 25, 2023 CPython 3.11 Windows x86-64

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

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 25, 2023 CPython 3.11 macOS 11.0+ ARM64

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

Uploaded Aug 25, 2023 CPython 3.11 macOS 10.9+ x86-64

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

Uploaded Aug 25, 2023 CPython 3.10 Windows x86-64

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

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 25, 2023 CPython 3.10 macOS 11.0+ ARM64

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

Uploaded Aug 25, 2023 CPython 3.10 macOS 10.9+ x86-64

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

Uploaded Aug 25, 2023 CPython 3.9 Windows x86-64

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

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 25, 2023 CPython 3.9 macOS 11.0+ ARM64

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

Uploaded Aug 25, 2023 CPython 3.9 macOS 10.9+ x86-64

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

Uploaded Aug 25, 2023 CPython 3.8 Windows x86-64

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

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 26, 2023 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 hashes)

Uploaded Aug 25, 2023 CPython 3.8 macOS 11.0+ ARM64

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

Uploaded Aug 25, 2023 CPython 3.8 macOS 10.9+ x86-64

Hashes for grad_tts-0.0.4.tar.gz

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

Hashes for grad_tts-0.0.4-cp311-cp311-win_amd64.whl

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

Hashes for grad_tts-0.0.4-cp311-cp311-musllinux_1_1_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp311-cp311-musllinux_1_1_i686.whl

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

Hashes for grad_tts-0.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp311-cp311-macosx_11_0_arm64.whl

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

Hashes for grad_tts-0.0.4-cp311-cp311-macosx_10_9_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp310-cp310-win_amd64.whl

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

Hashes for grad_tts-0.0.4-cp310-cp310-musllinux_1_1_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp310-cp310-musllinux_1_1_i686.whl

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

Hashes for grad_tts-0.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp310-cp310-macosx_11_0_arm64.whl

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

Hashes for grad_tts-0.0.4-cp310-cp310-macosx_10_9_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp39-cp39-win_amd64.whl

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

Hashes for grad_tts-0.0.4-cp39-cp39-musllinux_1_1_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp39-cp39-musllinux_1_1_i686.whl

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

Hashes for grad_tts-0.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp39-cp39-macosx_11_0_arm64.whl

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

Hashes for grad_tts-0.0.4-cp39-cp39-macosx_10_9_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp38-cp38-win_amd64.whl

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

Hashes for grad_tts-0.0.4-cp38-cp38-musllinux_1_1_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp38-cp38-musllinux_1_1_i686.whl

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

Hashes for grad_tts-0.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

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`

Hashes for grad_tts-0.0.4-cp38-cp38-macosx_11_0_arm64.whl

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

Hashes for grad_tts-0.0.4-cp38-cp38-macosx_10_9_x86_64.whl

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`