Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

update outetts according new repo structure #2569

Merged
merged 3 commits into from
Nov 29, 2024
Merged

update outetts according new repo structure #2569

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3bf0edb
update outetts according new repo structure
eaidova Nov 29, 2024
b481945
skip python 3.9
eaidova Nov 29, 2024
c532f91
Update skipped_notebooks.yml
eaidova Nov 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .ci/skipped_notebooks.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -552,6 +552,8 @@
skips:
- os:
- macos-13
- python:
- '3.9'
- notebook: notebooks/mobileclip-video-search/mobileclip-video-search.ipynb
skips:
- os:
Expand All @@ -562,4 +564,4 @@
- macos-13
- ubuntu-20.04
- ubuntu-22.04
- windows-2019
- windows-2019
215 changes: 75 additions & 140 deletions notebooks/outetts-text-to-speech/outetts-text-to-speech.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

23 changes: 18 additions & 5 deletions notebooks/outetts-text-to-speech/ov_outetts_helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,19 @@
from outetts.v0_1.interface import InterfaceHF
from outetts.v0_1.audio_codec import AudioCodec
from outetts.v0_1.prompt_processor import PromptProcessor
from outetts.v0_1.model import HFModel
import torch
from optimum.intel.openvino import OVModelForCausalLM

try:
from outetts.version.v1.interface import InterfaceHF
from outetts.version.v1.prompt_processor import PromptProcessor
from outetts.version.v1.model import HFModel
from outetts.wav_tokenizer.audio_codec import AudioCodec
updated_version = True
except ImportError:
from outetts.v0_1.interface import InterfaceHF
from outetts.v0_1.audio_codec import AudioCodec
from outetts.v0_1.prompt_processor import PromptProcessor
from outetts.v0_1.model import HFModel
updated_version = False


class OVHFModel(HFModel):
def __init__(self, model_path, device):
Expand All @@ -20,5 +29,9 @@ def __init__(
) -> None:
self.device = torch.device("cpu")
self.audio_codec = AudioCodec(self.device)
self.prompt_processor = PromptProcessor(model_path)
self.prompt_processor = PromptProcessor(model_path) if not updated_version else PromptProcessor(model_path, ["en"])
self.model = OVHFModel(model_path, device)
self.language = "en"
self.verbose = False
self.languages = ["en"]
self._device = torch.device("cpu")
Loading