luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #8 from pathintegral-institute/rong/tech-150-add-kwarg

Browse source 
make pydub an optional import
This commit is contained in:
rong-xyz 2025-04-24 14:57:24 +08:00 committed by GitHub
commit f9510656e0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 18 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -30,6 +30,12 @@ pip install git+https://github.com/pathintegral-institute/markitup.git@main#subd
uv add git+https://github.com/pathintegral-institute/markitup.git@main#subdirectory=packages/markitup uv add git+https://github.com/pathintegral-institute/markitup.git@main#subdirectory=packages/markitup
``` ```
To use audio transciption using `pydub`, install `markitup[audio]`:
```bash
uv add "git+https://github.com/pathintegral-institute/markitup.git@main#subdirectory=packages/markitup[audio]"
```
## Usage ## Usage
```python ```python
from markitup.converter_utils.utils import read_files_to_bytestreams from markitup.converter_utils.utils import read_files_to_bytestreams

11
packages/markitup/pyproject.toml
View file

@ -34,13 +34,22 @@ dependencies = [
"pandas", "pandas",
"lxml", "lxml",
"olefile", "olefile",
"pydub", # "pydub", <- Removed from here
"SpeechRecognition", "SpeechRecognition",
"pymupdf>=1.25.5", "pymupdf>=1.25.5",
"openpyxl>=3.1.5", "openpyxl>=3.1.5",
"xlrd>=2.0.1", "xlrd>=2.0.1",
] ]
[project.optional-dependencies]
audio = [
"pydub",
]
# Optional: You may want to create an 'all' extra that includes all optional dependencies
all = [
"pydub",
]
[tool.hatch.version] [tool.hatch.version]
path = "src/markitup/__about__.py" path = "src/markitup/__about__.py"

4
packages/markitup/src/markitup/converter_utils/utils.py
View file

@ -1,9 +1,6 @@
import os import os
from io import BytesIO from io import BytesIO
from markitup._schemas import StreamInfo
import magic
import speech_recognition as sr import speech_recognition as sr
import pydub
import io import io
from typing import BinaryIO from typing import BinaryIO
@ -47,6 +44,7 @@ def transcribe_audio(file_stream: BinaryIO, *, magic_type: str = "audio/mpeg") -
match audio_format: match audio_format:
case 'mp3': case 'mp3':
import pydub
audio_segment = pydub.AudioSegment.from_file( audio_segment = pydub.AudioSegment.from_file(
file_stream, format=audio_format) file_stream, format=audio_format)
audio_source = io.BytesIO() audio_source = io.BytesIO()