b'
In this eisode we discuss more of L3arbi, that was resented by the DevoxxMA team at the vent, from a technical point of view with Nouamane and Faissal.
\\nGuests
\\nNotes
\\n0:00:00\\xa0- Introduction and welcoming
\\n0:01:21\\xa0- Who/what is l3arbi?
\\n0:16:24\\xa0- Is there possibilties that L3arbi will learn other arabic dialects other than darija?
\\n0:26:35\\xa0- Challenges of audio transcription
\\n0:27:31\\xa0- Live demo of L3arbi
\\n0:32:56\\xa0- Data training and Whisper and how many hours of darija data is used ?
\\n0:34:30\\xa0- Format of data that is used for training, and arcitecture of web application presented in DevoxxMA
\\n0:39:37\\xa0- The use case of DevoxxMA
\\n0:44:30\\xa0- Finetuning of an LLM, models and details
\\n0:56:20\\xa0- Evaluation set for different dialects per regions in morocco
\\n1:03:31\\xa0- Did you use manual transcription for the audio sets ?
\\n1:12:09\\xa0- The future plans of data sources for L3arbi solution.
\\n1:15:12\\xa0- Plans to open-source? Are there APIs available for developers to extend its functionality?
\\n1:25:00\\xa0- QA & Giveaway
\\n1:59:40\\xa0- Conclusion and goodbye.
\\nLinks
\\nPrepared and Presented by
\\n