Add Text-To-Speech pipeline #24952
add AutoModelForTextToSpeech class
dc69e3a3
add TTS pipeline and tessting
45bb44cc
add docstrings to text_to_speech pipeline
7fb82608
fix torch dependency
b0283836
corrector 'processor is None' case in Pipeline
59aa1f50
correct repo id
7360555a
Narsil
commented
on 2023-07-21
Merge branch 'huggingface:main' into add_tts_pipeline
c2eae25b
modify text-to-speech -> text-to-audio
57ea0b3b
remove processor
17d618c9
rename text_to_speech pipelines files to text_audio
6c80743a
add textToWaveform and textToSpectrogram instead of textToAudio classes
b43a1f2b
update TTS pipeline to the bare minimum
01abc20e
update tests TTS pipeline
7f96a848
make style and erase useless import torch in TTS pipeline tests
d6f00131
Narsil
approved these changes
on 2023-08-02
modify how to check if generate or forward in TTS pipeline
7e141278
remove unnecessary extra new lines
71f99482
Apply suggestions from code review
72142ead
refactor input_texts -> text_inputs
c8d8a7b8
correct docstrings of TTS.__call__
59e92498
correct the shape of generated waveform
29f7dfbd
take care of Bark tokenizer special case
c642d5fb
correct run_pipeline_test TTS
df8dd607
make style
a93f19c6
update TTS docstrings
9c5ffc04
address Sylvain nit refactors
179e5c2d
make style
a0de4651
refactor into one liners
f6f37023
sgugger
approved these changes
on 2023-08-11
Merge branch 'huggingface:main' into add_tts_pipeline
71b7832a
Merge branch 'huggingface:main' into add_tts_pipeline
62a53a9f
correct squeeze
a67632a6
correct way to test if forward or generate
9948d5b0
Update output audio waveform shape
2d7154ae
make style
9ec61fae
Merge branch 'huggingface:main' into add_tts_pipeline
c906e42b
correct import
72d606fc
modify how the TTS pipeline test if a model can generate
ed7ad070
align shape output of TTS pipeline with consistent shape
0c5d4de3
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub