Tiro TTS web service (22.10)

Ragnarsson, Róbert Kjaran; Guðmundsson, Smári Freyr

Tiro TTS web service (22.10)

Clarin IS Repository

Authors: Ragnarsson, Róbert Kjaran and Guðmundsson, Smári Freyr

Item identifier: http://hdl.handle.net/20.500.12537/268

Project URL: https://github.com/tiro-is/tiro-tts/releases/tag/M9

Date issued: 2022-09-26

Type: toolService

Description: Tiro TTS is a text-to-speech (TTS) API web service that works with various TTS backends. By default, it expects a FastSpeech2+Melgan+IceG2P backend. See the https://github.com/cadia-lvl/fastspeech2 repository for more information on the backend. The service can accept either unnormalized text or an SSML document and respond with audio (MP3, Ogg Vorbis or raw 16 bit PCM) or speech marks, indicating the byte and time offset of each synthesized word in the request. The full API documentation in OpenAPI 2 format is available online at tts.tiro.is. The code for the service along with further information is on https://github.com/tiro-is/tiro-tts/releases/tag/M9. You should also check if a newer version is out (see README.md)

ÍSLENSKA: Tiro Talgervill er vefgátt fyrir talgervingu (TTS). Vefgáttin ræður við ýmsar tegundir talgervilslíkana. Sjálfgefna stillingin gerir ráð fyrir FastSpeech2+Melgan+IceG2P TTS líkani. Sjá https://github.com/cadia-lvl/fastspeech2 Git-lindina fyrir meiri upplýsingar um líkanið. Vefgáttinn gerir notendum kleift að gera köll með forritaskilum þar sem notandinn sendir inn ónormaðan texta eða SSML skrá og fær til baka svar í formi hljóðskráar (MP3, Ogg Vorbis eða hrátt 16 bita PCM) með samsvarandi tali eða gögn um tímasetningu hvers mælts orðs. Skjölun forritunarskila þjónustunnar á OpenAPI 2 sniði er að finna á tts.tiro.is. Vefgáttin, ásamt frekari upplýsingum, er aðgengileg á https://github.com/tiro-is/tiro-tts/releases/tag/M9. Einnig er gott að athuga þar hvort ný útgáfa sé komin út (sjá README.md).

Publisher: Tiro

Subject(s): TTS tts text-to-speech web service

Collection(s): Clarin IS

Other versions

Show full item record

Files in this item

This item is

Publicly Available

and licensed under:
Apache License 2.0

Name: tiro-tts-M9.zip
Size: 58.99 MB
Format: application/zip
Description: Code for Tiro TTS
MD5: c240e344687501ad42c7a28fb7af535b

Download file Preview

File Preview

tiro-tts-M9
- LICENSE11 kB
- run.sh274 B
- patches
  - com_github_grpc_grpc
    - grpc_python_deps.bzl.patch536 B
    - cython_library.bzl.patch486 B
- .gitlab-ci.yml1 kB
- fetch_models.sh2 kB
- .flake8176 B
- k8s
  - overlays
    - prod
      - configmap.yaml104 B
      - kustomization.yaml293 B
      - ingress.yaml300 B
    - dev
      - configmap.yaml109 B
      - kustomization.yaml345 B
      - ingress.yaml305 B
  - base
    - service.yaml154 B
    - kustomization.yaml59 B
    - ingress.yaml304 B
    - deployment.yaml1 kB
  - BUILD2 kB
- WORKSPACE857 B
- migrations
  - versions
    - 8058672753e9_initial_migration.py924 B
    - b2b13821f9f4_added_the_rest_of_the_tables_users_.py1 kB
  - README.md1 kB
  - env.py2 kB
  - __init__.py149 B
  - alembic.ini857 B
  - script.py.mako494 B
- workspace2.bzl967 B
- .bazelrc391 B
- design
  - auth.md9 kB
  - schema.drawio6 kB
- mypy.ini36 B
- proto
  - tiro
    - tts
      - voice.proto5 kB
      - BUILD343 B
- manage_db.py21 kB
- pyproject.toml237 B
- generated
  - .gitkeep0 B
- repositories.bzl17 kB
- src
  - gunicorn_runner.py223 B
  - models
    - key.py1 kB
    - user.py1 kB
    - project.py1 kB
    - tts_request.py1 kB
  - logging_utils.py317 B
  - __init__.py3 kB
  - frontend
    - words.py30 kB
    - __init__.py573 B
    - tests
      - __init__.py0 B
      - test_phonemes.py4 kB
      - test_mdl_grapheme_to_phoneme.py8 kB
      - test_words.py1 kB
      - test_ssml.py1 kB
      - test_normalization.py13 kB
      - test_mdl_lexicon.py6 kB
      - test_common.py2 kB
      - test_grapheme_to_phoneme.py3 kB
    - lexicon.py6 kB
    - normalization.py16 kB
    - grapheme_to_phoneme.py11 kB
    - phonemes.py5 kB
    - ssml.py7 kB
    - common.py15 kB
  - tests
    - synthesis_set_test.pbtxt657 B
    - test_end2end.py12 kB
  - auth
    - api_key.py630 B
  - scripts
    - fastspeech_convert.py8 kB
    - melgan_convert.py2 kB
  - ffmpeg.py5 kB
  - voices
    - fastspeech.py11 kB
    - tests
      - test_espnet2.py1 kB
    - aws.py2 kB
    - voice_base.py2 kB
    - utils.py1 kB
    - __init__.py672 B
    - manager.py7 kB
    - espnet2.py10 kB
  - config.py1 kB
  - app.py7 kB
  - lib
    - fastspeech
      - train.py12 kB
      - README.md8 kB
      - align_phonemes.py6 kB
      - .gitignore1 kB
      - tensorboard.png125 kB
      - hparams.py2 kB
      - loss.py1 kB
      - g2p_is.py1 kB
      - synthesize.py8 kB
      - index.html12 kB
      - fastspeech2.py4 kB
      - dataset.py4 kB
      - model.png331 kB
      - melgan
        README.md3 kB
        .gitignore1 kB
        config
        default.yaml622 B
        datasets
        dataloader.py2 kB
        assets
        lj-tensorboard-v0.3-alpha.png59 kB
        lj-tensorboard.png43 kB
        gd.png110 kB
        model
        multiscale.py800 B
        identity.py206 B
        res_stack.py1 kB
        generator.py3 kB
        discriminator.py2 kB
        requirements.txt69 B
        inference.py1 kB
        trainer.py1 kB
        utils
        train.py5 kB
        utils.py578 B
        audio_processing.py2 kB
        hparams.py1 kB
        stft.py7 kB
        writer.py1 kB
        validation.py1 kB
        plotting.py740 B
        LICENSE1 kB
        preprocess.py1 kB
        hubconf.py1 kB
      - preprocess.py1 kB
      - text
        __init__.py2 kB
        numbers.py2 kB
        symbols.py775 B
        cmudict.py2 kB
        cleaners.py2 kB
      - utils.py6 kB
      - modules.py7 kB
      - transformer
        Modules.py653 B
        Models.py5 kB
        SubLayers.py2 kB
        Constants.py108 B
        Layers.py4 kB
        __init__.py137 B
      - evaluate.py7 kB
      - runtime.Dockerfile641 B
      - prepare_align.py399 B
      - requirements.txt282 B
      - LICENSE1 kB
      - optimizer.py1 kB
      - audio
        __init__.py67 B
        audio_processing.py2 kB
        tools.py2 kB
        stft.py6 kB
      - data
        blizzard2013.py4 kB
        ljspeech.py4 kB
        talromur.py4 kB
  - utils
    - version.py1 kB
  - templates
    - index.dhtml664 B
  - middleware
    - request_id.py1 kB
    - __init__.py628 B
  - schemas.py9 kB
- pytest.ini76 B
- workspace1.bzl953 B
- pyrightconfig.json97 B
- tools
  - kubectl44 MB
  - bazel48 MB
  - py
    - py_repl.bzl4 kB
    - defs.bzl2 kB
    - py_pytest_test.bzl1 kB
    - pytest_helper.py88 B
    - BUILD203 B
- manage_db.sh115 B
- .dir-locals.el677 B
- requirements.bazel.in640 B
- main.py311 B
- Dockerfile1 kB
- conf
  - synthesis_set.local.pbtxt2 kB
  - synthesis_set.pbtxt2 kB
- requirements.bazel.txt96 kB
- BUILD7 kB
- README.md6 kB
- .bazelignore55 B
- .gitlab
  - ci.bazelrc295 B
- .gitignore102 B
- .dockerignore43 B

Tiro TTS web service (22.10)

Files in this item

Partners, Coordination, Funding

Repository

More