Karsamanja/paza-whisper-large-v3-turbo-swahili-english-cs

automatic-speech-recognition model by Karsamanja

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

LoRA adaptation of Microsoft's Paza Whisper Large-v3-Turbo using conversational Swahili-English code-switched speech. Whisper-small WER: 648.53% Whisper Large-v3-Turbo WER: 234.49% Paza Large-v3-Turbo WER: 1294.11% Fine-tuned Paza WER: 72.44% Absolute WER change: 1221.66 percentage points Relative WER reduction: 94.40% liva-ai/swahili-english-asr https://huggingface.co/datasets/liva-ai/swahili-english-asr This is a small…

Karsamanja/paza-whisper-large-v3-turbo-swahili-english-cs on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-02T08:27:30.212Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Karsamanja/paza-whisper-large-v3-turbo-swahili-english-cs is a automatic-speech-recognition model repository published by Karsamanja on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: automatic-speech-recognition
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 808,884,480
Architecture: WhisperForConditionalGeneration
License: Not reported — check the model card
Access: Not gated by Hugging Face
Created: 2026-10-02T06:10:36.000Z
Last modified: 2026-10-02T06:10:58.000Z

Compatibility and lineage

Reported languages: sw, en

Reported base models: microsoft/paza-whisper-large-v3-turbo

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion