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.

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

Feature/voice analysis #30

Open
wants to merge 25 commits into
base: main
Choose a base branch
from
Open

Feature/voice analysis #30

wants to merge 25 commits into from

Conversation

Nathanlauga
Copy link
Collaborator

No description provided.

@DnzzL DnzzL force-pushed the feature/voice_analysis branch from 6177b88 to f9ffc8e Compare February 1, 2023 15:53
@DnzzL DnzzL force-pushed the feature/voice_analysis branch from dd79922 to ecf17c6 Compare February 13, 2023 13:12
@DnzzL DnzzL force-pushed the feature/voice_analysis branch from ecf17c6 to fe3f487 Compare February 13, 2023 13:14
@Lokhia Lokhia marked this pull request as ready for review February 23, 2023 18:52
@Lokhia Lokhia requested a review from TheoLvs February 23, 2023 18:52
Copy link
Collaborator

@TheoLvs TheoLvs left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hello,

Pas mal de choses à revoir dans cette PR @Lokhia @DnzzL avant de la merge sur main. Le plus important c'est qu'elle ne respecte pas pour le moment les conventions du repo c'est à dire en philosophie librairie avec des modules interopérables. Il faut qu'on puisse facilement pouvoir faire
``from bechdelai.audio import ...```
Sinon ça va être impossible à déployer et à rendre interopérable avec le reste.
Les autres commentaires sont dans les fichiers.

Aussi on va rajouter une règle, il faut qu'on ait un notebook qui explique les fonctionnalités dans le dossier racine tutorials avant d'être validé sur main (parce qu'à terme c'est ce qui partira en prod sur PyPi).

En attendant sur la partie audio pour la démo restons sur la branche feature/voice_analysis le temps de le faire évoluer proprement :)

bechdelai/audio/main.py Outdated Show resolved Hide resolved
bechdelai/audio/dependencies.py Outdated Show resolved Hide resolved
bechdelai/audio/OLD/speech_transcriber.py Outdated Show resolved Hide resolved
bechdelai/audio/audio_processor.py Outdated Show resolved Hide resolved
bechdelai/audio/dialogue_tagger.py Show resolved Hide resolved
pyproject.toml Outdated Show resolved Hide resolved
pyproject.toml Outdated
@@ -1,12 +1,12 @@
[tool.poetry]
name = "bechdelai"
version = "0.0.1-alpha.2"
version = "0.1.0"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Restons sur une version 0.0.2 pour le prochain bump

pyproject.toml Outdated Show resolved Hide resolved
openpyxl = "^3.0.10"
pytube = "^12.1.0"
mediapipe = "^0.9.0"
scenedetect = {extras = ["opencv"], version = "^0.6.1"}
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Il faut garder ces versions dans le merge

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pareil.

pyproject.toml Show resolved Hide resolved
bechdelai/audio/OLD/gender_identifier.py Outdated Show resolved Hide resolved
bechdelai/audio/OLD/speech_transcriber.py Outdated Show resolved Hide resolved
columns=['gender', 'start', 'end'])


def _convert_whisper_output(self,segments:pd.DataFrame) -> list:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

je trouve le nom de la fonction pas hyper clair

print("Could not request results from Google Speech Recognition service; {0}".format(e))


class WhisperAPI(Transcriber):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

j'aimerais bien de la docstring pour clarifier l'usage entre WhisperAPI et Whisper

from moviepy.video.io.ffmpeg_tools import ffmpeg_extract_subclip


def cut_and_save(movie_path: str, start: float, end: float, target_name: str) -> None:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Up ? :)

Comment on lines 1 to 4
path_to_extract=<path_to_extract_file>
path_to_audio=<path_to_audio_file>
path_to_full_movie=<path_to_full_movie_file>
path_to_trailer=<path_to_trailer_file>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OLD à supprimer ?

Comment on lines 1 to 9
#Readme pour l'audio
## Installation
* .env
* créer un fichier ".env" en local pour y placer le chemin vers la vidéo, comme dans .env.example
* poetry update / poetry install
* poetry run python .\gender_identification.py
* ffmpeg codex (pour Windows, suivre les instructions [ici](https://www.geeksforgeeks.org/how-to-install-ffmpeg-on-windows/) -
pas besoin de mettre à la racine en admin et de redémarrer ;
pour ubuntu `$ sudo apt-get install ffmpeg`, voir la [doc du projet](https://github.com/ina-foss/inaSpeechSegmenter))
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pareil

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants