OpenAI Whisper Model for Audio Transcription
Budget: $50 – $0 USD
We are looking for someone who is specialized in building/fine-tunning Openai Whisper model for audio transcription. To be specific, we are interested in either building or fine tunning models for special dialects. Please provide a clear milestone that illustraate the work procedure.
- The purpose of this project is to have full knowledge about building/fune-tunning Openai Whisper models.
- The freelancer should be capable of answering and clarifying all the questions/concerns related to selected choice (model details such as number of layers and other model parameters).
- The freelancer should be capable of justifying the reasons behind the selection between fine-tunnnig or building a model from scratch based on the required task (audio transcription).
- Define all the requirements needed for dataset preparations such as feature normalization, data padding, etc...
- The purpose of this project is to have full knowledge about building/fune-tunning Openai Whisper models.
- The freelancer should be capable of answering and clarifying all the questions/concerns related to selected choice (model details such as number of layers and other model parameters).
- The freelancer should be capable of justifying the reasons behind the selection between fine-tunnnig or building a model from scratch based on the required task (audio transcription).
- Define all the requirements needed for dataset preparations such as feature normalization, data padding, etc...