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.

cdli/whisper-small_finetuned_kenyan_swahili_nonstandard_speech_v1.0

Record type:

model

Creator:

cdli

Host:

Visit

Tasks

automatic speech recognition speech processing

Languages

Tags

safetensors whisper

Similar

cdli/whisper-small-Swahili_finetuned_small_CV20cdli/whisper-large-v3_finetuned_ugandan_luganda_waxal_7_standard_speech_v1.0cdli/whisper-large-v3_finetuned_ugandan_luganda_nonstandard_speech_v1.0cdli/whisper-large-v3_finetuned_kenyan_swahili_nonstandard_speech_v1.0cdli/common_voice_swahili_smallcdli/kenyan_swahili_nonstandard_speech_v1.0

cdli/whisper-small-Swahili_finetuned_small_CV20

cdli/whisper-large-v3_finetuned_ugandan_luganda_waxal_7_standard_speech_v1.0

cdli/whisper-large-v3_finetuned_ugandan_luganda_nonstandard_speech_v1.0

cdli/whisper-large-v3_finetuned_kenyan_swahili_nonstandard_speech_v1.0

cdli/common_voice_swahili_small

Small dataset derived from Common Voice 20.0 (cv-corpus-22.0-2025-06-20) by selecting only utterance

cdli/kenyan_swahili_nonstandard_speech_v1.0

This dataset provides 32.5 hours of Swahili speech recordings (5,535 samples) from 52 Kenyan speaker