Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

KevKibe/Finetuning-WhisperSmall-LoRA-Swahili

Domain:

natural language processing

Record type:

model
Creator:
Kev
Host:
This repository features code for Swahili Automatic Speech Recognition (ASR) fine-tuning using the Whisper model on Swahili Common Voice dataset. # Swahili Automatic Speech Recognition (ASR) Experiment ## Description This repository features code for an experimental Swahili ```Automatic Speech Recognition (ASR)``` using the Whisper model. The primary aim is to fine-tune the model on Swahili speech data and evaluate its performance on this audio file. ## Fine-Tuning Approach The fine-tuning process employs ```Parameter Efficient Fine Tuning (PEFT)```, a method that selectively fine-tunes a minimal number of model parameters while keeping the majority frozen. This results in significantly reduced computational and storage costs. The specific technique used is ```Low Rank Adaptation (LoRA)```, which introduces trainable rank decomposition matrices into each layer of the Transformer architecture. ## Original Model Transcriptions The original model transcriptions for the audio file were ineffective, producing nonsensical outputs. Examples include: - ```"ช์หน้ามตอนนั้นต supplementalีเปล่าขolyแขนม benimบนับมัดไอตบึกมัดเลย"``` - ```"ซูครั้งส่ารัaksiตорошоปment this is my new day.วิทย์ดึง畢อะ ๆ"``` - ```"ชุครสธานตรเป็นод mosquitoes couldn'tวMUSIC ดัดิ่งที่ต้องล่ะของคลิทฝัnd นะไม่ of"``` ## Fine-Tuned Model Inference Post fine-tuning, the transcribed text returned was ```"Shukranisana pendo poni madandefu lakinimuda haukwa upandewezu,"``` aligning closely with the correct transcription: ```"Shukrani sana pendo poni mada ndefu lakini muda hauko upande wetu."``` This demonstrates notable improvement after a test run of 100 steps(30 mins). See details in the notebook. ## To get Inference ``` !pip install -q git+github.com !pip install accelerate !pip install bitsandbytes==0.37 !pip install torch from transformers import ( AutomaticSpeechRecognitionPipeline, WhisperForConditionalGeneration, WhisperTokenizer, WhisperProcessor, ) from peft import PeftModel, PeftConfig import torch peft_model_id = "KevinKibe/swahili-asr-whisper-small-LoRA-finetune-100steps" language = "sw" task = "trans …

Visit

github.com

Tasks

automatic speech recognitionspeech processing

Languages

Swahili

Licenses

MIT

Similar

Joshua-Abok/finetuning-wav2vec-lora-large-swahili-asr-model_v20Souadzriouil/darijabert-lora-finetuningleftie/finetuning-wav2vec-swahiliKevKibe/Chat-based-Interactions-with-Swahili-Audio-and-Videossmutuvi/finetuning-whisper-small-swahili-ablation_ndizi_CVsmutuvi/finetuning-whisper-tiny-swahili-ablation_ndizi_AfriVoice

Joshua-Abok/finetuning-wav2vec-lora-large-swahili-asr-model_v20

Souadzriouil/darijabert-lora-finetuning

This project focuses on fine-tuning DarijaBERT for Moroccan Darija text classification using LoRA (L

leftie/finetuning-wav2vec-swahili

KevKibe/Chat-based-Interactions-with-Swahili-Audio-and-Videos

This is an application that enables a chat-based conversation in English with Swahili videos/audio f

smutuvi/finetuning-whisper-small-swahili-ablation_ndizi_CV

smutuvi/finetuning-whisper-tiny-swahili-ablation_ndizi_AfriVoice