Africanwhisper

Updates
- Specify what number of samples you want in your train and test set using `test_num_samples` and `train_num_samples` in load_data module.
- All possible trainer parameters from the [Seq2SeqTrainingArguments](https://huggingface.co/docs/transformers/main_classes/trainer#transformers.Seq2SeqTrainingArguments) available when configuring training run.
What's Changed
* Update: Add `test_num_samples` and `train_num_samples` to load_data module. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/116


**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.9.2...v0.9.3

Improvements for Inference Pipeline for Fully Finetuned Models
- Model Optimization: Uses [CTranslate2](https://github.com/OpenNMT/CTranslate2) for optimized model performance.
- Backend: Leverages the [faster-whisper](https://github.com/SYSTRAN/faster-whisper) backend (previously based on the Transformers Pipeline) for faster processing.
- Alignment: Uses Wav2vec models to ensure precise audio alignment.
- Multi-Speaker Diarization: Integrates [pyannote-audio](https://github.com/pyannote/pyannote-audio) for speaker identification and labeling.
- Voice Activity Detection (VAD): Employs VAD preprocessing to reduce hallucination and improve batching without compromising Word Error Rate (WER).

Fixes
- Fixes 109

What's Changed
* Chore: Update deployment documentation, Fix: remove uid by KevKibe in https://github.com/KevKibe/African-Whisper/pull/93
* Chore: Add unittests for `training.whisper_model_prep` module. Modify `training.load_dataset` module by KevKibe in https://github.com/KevKibe/African-Whisper/pull/94
* Chore: Add tests for `training.audio_data_processor` module. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/95
* Feat: Faster Whisper backend for `deployment.transcription_pipeline` module, transcription alignment, audio diarization, VAD. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/98
* Chore: Update `DOCS/DEPLOYMENT.MD` and comments, add faster-whisper dependencies to `src/deployments/requirements.txt`.`. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/100
* Bump rustls from 0.22.3 to 0.22.4 in /src/deployment/rustinference by dependabot in https://github.com/KevKibe/African-Whisper/pull/99
* Refactors: Change filenames for easier identification of peft code and non-peft. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/102
* Fix: 'argparse` argument name, update version number for new release by KevKibe in https://github.com/KevKibe/African-Whisper/pull/107
* Fix: `whisper_arch` parameter in `load_asr_model` in `convert_model_to_optimized_format` method. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/110
* Chore: Add tests for `deployment.peft_speech_inference` module, fix `src/deployment/speech_inference_cli.py`. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/111
* Feat: Add `num_samples` parameter to `training.load_data` module to load a section of the training data. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/112
* Fix: `src/deployment/faster_whisper/mel_filters.npz` file in build. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/113


**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.9.0...v0.10.0

Release Highlights
This release updates the deployment module by separating inference for PEFT finetuned models and fully finetuned models.<br>
For more information, refer to [deployment.md](https://github.com/KevKibe/African-Whisper/blob/master/DOCS/deployment.md)

Improvements for Inference Pipeline for Fully Finetuned Models
- Model Optimization: Uses [CTranslate2](https://github.com/OpenNMT/CTranslate2) for optimized model performance.
- Backend: Leverages the [faster-whisper](https://github.com/SYSTRAN/faster-whisper) backend (previously based on the Transformers Pipeline) for faster processing.
- Alignment: Uses Wav2vec models to ensure precise audio alignment.
- Multi-Speaker Diarization: Integrates [pyannote-audio](https://github.com/pyannote/pyannote-audio) for speaker identification and labeling.
- Voice Activity Detection (VAD): Employs VAD preprocessing to reduce hallucination and improve batching without compromising Word Error Rate (WER).

**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.9.0...v0.9.1

Release Highlights
- This update introduces Prometheus and Grafana monitoring to the inference API located in `src/deployment/main` dubbed `speech_inference`.
- `speech_inference`'s function is to either `translate` or `transcribe` an audiofile.



What's Changed
* Add Prometheus and Grafana monitoring to inference API in `src/deployment/main` by KevKibe in https://github.com/KevKibe/African-Whisper/pull/90
* Update setup.cfg version number by KevKibe in https://github.com/KevKibe/African-Whisper/pull/91
* Delete datasource uid by KevKibe in https://github.com/KevKibe/African-Whisper/pull/92


**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.8.0...v0.9.0

Release Highlights
- `wandb` version update to `0.16.6` .
- `uvicorn` and `fastapi` update to build.
- Tests for `training.load_data` module.

What's Changed
* build(deps): bump wandb from 0.16.5 to 0.16.6 by dependabot in https://github.com/KevKibe/African-Whisper/pull/68
* Chore: Tests for `training.load_data` module. by KevKibe in https://github.com/KevKibe/African-Whisper/pull/86
* Update setup.cfg to include uvicorn and fastapi dependencies by KevKibe in https://github.com/KevKibe/African-Whisper/pull/87
* Fix: update workflows to run on pull request only by KevKibe in https://github.com/KevKibe/African-Whisper/pull/88


**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.7.0...v0.8.0

Bug Fix
- Fixes `Pydantic` bug in inference pipeline.

What's Changed
* Revert `inference.py` back to loading model without AutoModelForSpeechSeq2Seq and Au… by KevKibe in https://github.com/KevKibe/African-Whisper/pull/84
* Update package version to `0.7.0` by KevKibe in https://github.com/KevKibe/African-Whisper/pull/85


**Full Changelog**: https://github.com/KevKibe/African-Whisper/compare/v0.6.0...v0.7.0