ElizabethMwangi/whisper-large-v3-swahili-nss-afrivoice-edu

Whisper Large V3 — Swahili NSS (AfriVoice Education Domain)

Stage 2 nonstandard speech fine-tune of openai/whisper-large-v3 on the CDLI Kenyan Swahili Nonstandard Speech dataset. Built on top of ElizabethMwangi/whisper-large-v3-swahili-afrivoice, a Stage 1 checkpoint trained on AfriVoice education-domain speech.

Training Details

• —Stage 1 base: ElizabethMwangi/whisper-large-v3-swahili-afrivoice (AfriVoice education domain)
• —Stage 2 dataset: cdli/kenyanswahilinonstandardspeechv1.0 (849 examples)
• —Language token: sw
• —Full model training: encoder, decoder, and projection updated
• —SpecAugment: On
• —Learning rate: 5e-5 (polynomial decay, warmup 40 steps)
• —Max steps: 1000
• —Best checkpoint: step 750
• —Output dir: swnsstunewhisperv3largeafrivoice_v1.1

Results on Kenyan Swahili Nonstandard Speech (test set, best checkpoint)

Overall, compared to unadapted baseline

By severity