videopython 0.2.1__tar.gz → 0.4.0__tar.gz

{videopython-0.2.1 → videopython-0.4.0}/.gitignore

@@ -137,4 +137,7 @@ dmypy.json
 # Data directories
 data/downloaded/*.mp4
 data/exported/*.mp4
-!data/exported/example.mp4
+!data/exported/example.mp4
+
+# Mac 
+*.DS_Store

{videopython-0.2.1 → videopython-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: videopython
-Version: 0.2.1
+Version: 0.4.0
 Summary: Minimal video generation and processing library.
 Project-URL: Homepage, https://github.com/bartwojtowicz/videopython/
 Project-URL: Repository, https://github.com/bartwojtowicz/videopython/
@@ -19,20 +19,8 @@ Requires-Dist: numpy>=1.25.2
 Requires-Dist: opencv-python>=4.9.0.80
 Requires-Dist: pillow>=10.3.0
 Requires-Dist: pydub>=0.25.1
+Requires-Dist: soundpython>=0.1.11
 Requires-Dist: tqdm>=4.66.3
-Provides-Extra: dev
-Requires-Dist: black==24.3.0; extra == 'dev'
-Requires-Dist: isort==5.12.0; extra == 'dev'
-Requires-Dist: mypy==1.8.0; extra == 'dev'
-Requires-Dist: pydub-stubs==0.25.1.1; extra == 'dev'
-Requires-Dist: pytest==7.4.0; extra == 'dev'
-Requires-Dist: types-pillow==10.2.0.20240213; extra == 'dev'
-Requires-Dist: types-tqdm==4.66.0.20240106; extra == 'dev'
-Provides-Extra: generation
-Requires-Dist: accelerate>=0.29.2; extra == 'generation'
-Requires-Dist: diffusers>=0.26.3; extra == 'generation'
-Requires-Dist: torch>=2.1.0; extra == 'generation'
-Requires-Dist: transformers>=4.38.1; extra == 'generation'
 Description-Content-Type: text/markdown
 
 # About
@@ -51,10 +39,10 @@ sudo apt-get install ffmpeg
 
 ### Install with pip
 ```bash
-pip install videopython[generation]
+pip install videopython[ai]
 ```
-> You can install without `[generation]` dependencies for basic video handling and processing. 
-> The funcionalities found in `videopython.generation` won't work.
+> You can install without `[ai]` dependencies for basic video handling and processing. 
+> The funcionalities found in `videopython.ai` won't work.
 
 ## Basic Usage
 
@@ -64,10 +52,10 @@ pip install videopython[generation]
 from videopython.base.video import Video
 
 # Load videos and print metadata
-video1 = Video.from_path("tests/test_data/fast_benchmark.mp4")
+video1 = Video.from_path("tests/test_data/small_video.mp4")
 print(video1)
 
-video2 = Video.from_path("tests/test_data/slow_benchmark.mp4")
+video2 = Video.from_path("tests/test_data/big_video.mp4")
 print(video2)
 
 # Define the transformations
@@ -91,18 +79,18 @@ savepath = video.save()
 
 ### Video Generation
 
-> Using Nvidia A40 or better is recommended for the `videopython.generation` module.
+> Using Nvidia A40 or better is recommended for the `videopython.ai` module.
 ```python
 # Generate image and animate it
-from videopython.generation import ImageToVideo
-from videopython.generation import TextToImage
-from videopython.generation import TextToMusic
+from videopython.ai.generation import ImageToVideo
+from videopython.ai.generation import TextToImage
+from videopython.ai.generation import TextToMusic
 
 image = TextToImage().generate_image(prompt="Golden Retriever playing in the park")
 video = ImageToVideo().generate_video(image=image, fps=24)
 
 # Video generation directly from prompt
-from videopython.generation import TextToVideo
+from videopython.ai.generation import TextToVideo
 video_gen = TextToVideo()
 video = video_gen.generate_video("Dogs playing in the snow")
 for _ in range(10):

{videopython-0.2.1 → videopython-0.4.0}/README.md

@@ -14,10 +14,10 @@ sudo apt-get install ffmpeg
 
 ### Install with pip
 ```bash
-pip install videopython[generation]
+pip install videopython[ai]
 ```
-> You can install without `[generation]` dependencies for basic video handling and processing. 
-> The funcionalities found in `videopython.generation` won't work.
+> You can install without `[ai]` dependencies for basic video handling and processing. 
+> The funcionalities found in `videopython.ai` won't work.
 
 ## Basic Usage
 
@@ -27,10 +27,10 @@ pip install videopython[generation]
 from videopython.base.video import Video
 
 # Load videos and print metadata
-video1 = Video.from_path("tests/test_data/fast_benchmark.mp4")
+video1 = Video.from_path("tests/test_data/small_video.mp4")
 print(video1)
 
-video2 = Video.from_path("tests/test_data/slow_benchmark.mp4")
+video2 = Video.from_path("tests/test_data/big_video.mp4")
 print(video2)
 
 # Define the transformations
@@ -54,18 +54,18 @@ savepath = video.save()
 
 ### Video Generation
 
-> Using Nvidia A40 or better is recommended for the `videopython.generation` module.
+> Using Nvidia A40 or better is recommended for the `videopython.ai` module.
 ```python
 # Generate image and animate it
-from videopython.generation import ImageToVideo
-from videopython.generation import TextToImage
-from videopython.generation import TextToMusic
+from videopython.ai.generation import ImageToVideo
+from videopython.ai.generation import TextToImage
+from videopython.ai.generation import TextToMusic
 
 image = TextToImage().generate_image(prompt="Golden Retriever playing in the park")
 video = ImageToVideo().generate_video(image=image, fps=24)
 
 # Video generation directly from prompt
-from videopython.generation import TextToVideo
+from videopython.ai.generation import TextToVideo
 video_gen = TextToVideo()
 video = video_gen.generate_video("Dogs playing in the snow")
 for _ in range(10):

{videopython-0.2.1 → videopython-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "videopython"
-version = "0.2.1"
+version = "0.4.0"
 description = "Minimal video generation and processing library."
 authors = [
     { name = "Bartosz Wójtowicz", email = "bartoszwojtowicz@outlook.com" },
@@ -24,24 +24,27 @@ dependencies = [
     "opencv-python>=4.9.0.80",
     "pillow>=10.3.0",
     "pydub>=0.25.1",
+    "soundpython>=0.1.11",
     "tqdm>=4.66.3",
+    
 ]
 
-[project.optional-dependencies]
+[dependency-groups]
 dev = [
-    "black==24.3.0",
-    "isort==5.12.0",
-    "mypy==1.8.0",
-    "pytest==7.4.0",
-    "types-Pillow==10.2.0.20240213",
-    "types-tqdm==4.66.0.20240106",
-    "pydub-stubs==0.25.1.1",
+    "ruff>=0.1.14",
+    "mypy>=1.8.0",
+    "pytest>=7.4.0",
+    "types-Pillow>=10.2.0.20240213",
+    "types-tqdm>=4.66.0.20240106",
+    "pytest-cov>=6.1.1",
 ]
-generation = [
+ai = [
     "accelerate>=0.29.2",
     "diffusers>=0.26.3",
     "torch>=2.1.0",
     "transformers>=4.38.1",
+    "openai-whisper>=20240930",
+    "numba>=0.61.0",
 ]
 
 [project.urls]
@@ -49,25 +52,8 @@ Homepage = "https://github.com/bartwojtowicz/videopython/"
 Repository = "https://github.com/bartwojtowicz/videopython/"
 Documentation = "https://github.com/bartwojtowicz/videopython/"
 
-[tool.rye]
-managed = true
-dev-dependencies = [
-    "black==24.3.0",
-    "isort==5.12.0",
-    "mypy==1.8.0",
-    "pytest==7.4.0",
-    "types-Pillow==10.2.0.20240213",
-    "types-tqdm==4.66.0.20240106",
-    "pydub-stubs==0.25.1.1",
-]
-
-[tool.rye.scripts]
-test-unit = "pytest"
-test-type = "mypy src"
-test-static = { chain = [
-    "black src -l 120 --check",
-    "isort src --profile black --check"
-]}
+[tool.mypy]
+mypy_path = "stubs"
 
 [build-system]
 requires = ["hatchling"]
@@ -79,10 +65,24 @@ packages = ["src/videopython"]
 [tool.hatch.build.targets.sdist]
 include = ["src/videopython", "src/videopython/py.typed"]
 
-[tool.mypy]
-mypy_path = "stubs"
-
 [tool.pytest]
+pythonpath = [".src/"]
 testpaths = ["src/tests"]
 python_files = ["test_*.py"]
 addopts = "-v --tb=short"
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+
+[tool.ruff.lint]
+select = [
+    "E",   # pycodestyle errors
+    "F",   # pyflakes
+    "I",   # isort
+]
+isort.known-first-party = ["videopython"]
+
+[tool.ruff.format]
+indent-style = "space"
+quote-style = "double"

{videopython-0.2.1/src/videopython → videopython-0.4.0/src/videopython/ai}/generation/audio.py

@@ -1,6 +1,5 @@
-import numpy as np
 import torch
-from pydub import AudioSegment
+from soundpython import Audio, AudioMetadata
 from transformers import (
     AutoProcessor,
     AutoTokenizer,
@@ -17,15 +16,24 @@ class TextToSpeech:
         self.pipeline = VitsModel.from_pretrained(TEXT_TO_SPEECH_MODEL)
         self.tokenizer = AutoTokenizer.from_pretrained(TEXT_TO_SPEECH_MODEL)
 
-    def generate_audio(self, text: str) -> AudioSegment:
+    def generate_audio(self, text: str) -> Audio:
         tokenized = self.tokenizer(text, return_tensors="pt")
 
         with torch.no_grad():
             output = self.pipeline(**tokenized).waveform
 
-        output = (output.T.float().numpy() * (2**31 - 1)).astype(np.int32)
-        audio = AudioSegment(data=output, frame_rate=self.pipeline.config.sampling_rate, sample_width=4, channels=1)
-        return audio
+        # Convert to float32 and normalize to [-1, 1]
+        audio_data = output.T.float().numpy()
+
+        metadata = AudioMetadata(
+            sample_rate=self.pipeline.config.sampling_rate,
+            channels=1,
+            sample_width=4,
+            duration_seconds=len(audio_data) / self.pipeline.config.sampling_rate,
+            frame_count=len(audio_data),
+        )
+
+        return Audio(audio_data, metadata)
 
 
 class TextToMusic:
@@ -37,7 +45,7 @@ class TextToMusic:
         self.processor = AutoProcessor.from_pretrained(MUSIC_GENERATION_MODEL_SMALL)
         self.model = MusicgenForConditionalGeneration.from_pretrained(MUSIC_GENERATION_MODEL_SMALL)
 
-    def generate_audio(self, text: str, max_new_tokens: int) -> AudioSegment:
+    def generate_audio(self, text: str, max_new_tokens: int) -> Audio:
         inputs = self.processor(
             text=[text],
             padding=True,
@@ -45,12 +53,16 @@ class TextToMusic:
         )
         audio_values = self.model.generate(**inputs, max_new_tokens=max_new_tokens)
         sampling_rate = self.model.config.audio_encoder.sampling_rate
-        output = (audio_values[0, 0].float().numpy() * (2**31 - 1)).astype(np.int32)
 
-        audio = AudioSegment(
-            data=output.tobytes(),
-            frame_rate=sampling_rate,
-            sample_width=4,
+        # Convert to float32 and normalize to [-1, 1]
+        audio_data = audio_values[0, 0].float().numpy()
+
+        metadata = AudioMetadata(
+            sample_rate=sampling_rate,
             channels=1,
+            sample_width=4,
+            duration_seconds=len(audio_data) / sampling_rate,
+            frame_count=len(audio_data),
         )
-        return audio
+
+        return Audio(audio_data, metadata)

{videopython-0.2.1/src/videopython → videopython-0.4.0/src/videopython/ai}/generation/image.py

@@ -1,6 +1,3 @@
-import io
-import os
-
 import torch
 from diffusers import DiffusionPipeline
 from PIL import Image

videopython-0.4.0/src/videopython/ai/understanding/transcribe.py

@@ -0,0 +1,37 @@
+from typing import Literal
+
+import whisper
+
+from videopython.base.transcription import Transcription, TranscriptionSegment
+from videopython.base.video import Video
+
+
+class VideoTranscription:
+    def __init__(self, model_name: Literal["tiny", "base", "small", "medium", "large", "turbo"] = "small") -> None:
+        self.model = whisper.load_model(name=model_name)
+
+    def transcribe_video(self, video: Video) -> Transcription:
+        """Transcribes video to text.
+
+        Args:
+            video: Video to transcribe.
+
+        Returns:
+            List of dictionaries with segments of text and their start and end times.
+        """
+        if video.audio.is_silent:
+            return Transcription(segments=[])
+
+        audio = video.audio.to_mono()
+        audio = audio.resample(whisper.audio.SAMPLE_RATE)
+        audio_data = audio.data
+
+        transcription = self.model.transcribe(audio=audio_data, word_timestamps=True)
+
+        transcription_segments = [
+            TranscriptionSegment(start=segment["start"], end=segment["end"], text=segment["text"])
+            for segment in transcription["segments"]
+        ]
+        result = Transcription(segments=transcription_segments)
+
+        return result

{videopython-0.2.1 → videopython-0.4.0}/src/videopython/base/effects.py

@@ -156,13 +156,13 @@ class Zoom(Effect):
 
         width = video.metadata.width
         height = video.metadata.height
-        crop_sizes_w, crop_sizes_h = np.linspace(width // self.zoom_factor, width, n_frames), np.linspace(
-            height // self.zoom_factor, height, n_frames
+        crop_sizes_w, crop_sizes_h = (
+            np.linspace(width // self.zoom_factor, width, n_frames),
+            np.linspace(height // self.zoom_factor, height, n_frames),
         )
 
         if self.mode == "in":
             for frame, w, h in tqdm(zip(video.frames, reversed(crop_sizes_w), reversed(crop_sizes_h))):
-
                 x = width / 2 - w / 2
                 y = height / 2 - h / 2
 

videopython-0.4.0/src/videopython/base/transcription.py

@@ -0,0 +1,13 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class TranscriptionSegment:
+    start: float
+    end: float
+    text: str
+
+
+@dataclass
+class Transcription:
+    segments: list[TranscriptionSegment]

{videopython-0.2.1 → videopython-0.4.0}/src/videopython/base/transforms.py

@@ -1,7 +1,6 @@
 from abc import ABC, abstractmethod
 from enum import Enum
 from multiprocessing import Pool
-from typing import Literal
 
 import cv2
 import numpy as np
@@ -154,7 +153,6 @@ class CropMode(Enum):
 
 
 class Crop(Transformation):
-
     def __init__(self, width: int, height: int, mode: CropMode = CropMode.CENTER):
         self.width = width
         self.height = height

{videopython-0.2.1 → videopython-0.4.0}/src/videopython/base/transitions.py

@@ -67,7 +67,7 @@ class FadeTransition(Transition):
             ],
             fps=video_fps,
         )
-        faded_videos.audio = videos[0].audio.append(videos[1].audio, crossfade=(effect_time_fps / video_fps) * 1000)
+        faded_videos.audio = videos[0].audio.concat(videos[1].audio, crossfade=(effect_time_fps / video_fps))
         return faded_videos
 
 
@@ -102,5 +102,5 @@ class BlurTransition(Transition):
             ],
             fps=video_fps,
         )
-        blurred_videos.audio = videos[0].audio.append(videos[1].audio)
+        blurred_videos.audio = videos[0].audio.concat(videos[1].audio)
         return blurred_videos