speakerbox

speakerbox copied to clipboard

Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 3 to 4. Release notes Sourced from codecov/codecov-action's releases. v4.0.0 v4 of the Codecov Action uses the CLI as the underlying upload. The CLI has helped to...

dependabot[bot]

accelerate or tranformers[torch] required

2

### Describe the Bug After a small training run, the program halted with the following error indicating a required library was missing. ### Expected Behavior Completion of training. ### Reproduction...

gregoryfoster

datasets ~=1.18 requirement introduces conflict w/ numpy > 1.23

3

### Describe the Bug `speakerbox` requires `datasets~=1.18` which in turn requires `numpy>=1.17`. The `datasets` `1.x` line hasn't been updated since mid-2022. `numpy` `v1.20` [deprecated use of aliases of built-in types](https://numpy.org/devdocs/release/1.24.0-notes.html#expired-deprecations)...

gregoryfoster

apply._diarize() does not allow for specification of Hugging Face token

2

### Describe the Bug The `apply()` function fails as a Hugging Face token is not supplied. The contained [`_diarize()` function calls](https://github.com/CouncilDataProject/speakerbox/blob/e9f1f4efd0199a5c0266873c345d11aa13d72ec8/speakerbox/main.py#L363): ```bash diarization_pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization") ``` This results in an...

gregoryfoster

pipenv install speakerbox retrieves v0.0.2 by default

2

### Describe the Bug When attempting an installation of the module, version 0.0.2 is installed by default. ### Expected Behavior PyPI has all of the versions, not sure why this...

gregoryfoster

Hi! First of all, thank you for developing SpeakerBox. It has proven to be an invaluable tool for my current project. Allow me to provide you with some context regarding...

squeipom

### Feature Description Support a more direct directory structure of speakers instead of "conversations". i.e.: ``` data/ ├── bob/ | ├── 0.wav | ├── 1.wav | ├── 2.wav | ├──...

evamaxfield

feature/any-audio-file-type

3

### Link to Relevant Issue This pull request resolves #14 ### Description of Changes Change only on 1 line, glob("*.wav") => chain of globs for every relevant audio file format....

NicolasMICAUX

`AudioSegment.from_file` is not restricted to WAV files

3

### Feature Description In `preprocess.py`, you use `AudioSegment.from_file` to load the audio files. According to [definition](https://github.com/jiaaro/pydub#quickstart) of this function, it seems it accepts a bunch of file formats. but at...

NicolasMICAUX