Downloads · 30 days
35
9% of all-time downloads
ai4good-labyrinth/fleurs-trigram-hours0p25-whisper-small-no-language
fleurs-trigram-hours0p25-whisper-small-no-language is a automatic speech recognition model from ai4good-labyrinth. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This repository contains a Whisper checkpoint for Chichewa/Nyanja automatic speech recognition, fine-tuned from openai/whisper-small.
Downloads · 30 days
35
9% of all-time downloads
All-time downloads
370
Public
Parameters
242M
967 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 99%
From the Hugging Face model README
This repository contains a Whisper checkpoint for Chichewa/Nyanja
automatic speech recognition, fine-tuned from openai/whisper-small.
fleurs-trigramopenai/whisper-smallno_languageThis checkpoint is intended for research and evaluation on Chichewa/Nyanja ASR. It is not a production-ready speech system and should be validated carefully before downstream use.
This repository contains a full fine-tuned checkpoint. It can be loaded directly with Transformers.
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
model_id = "ai4good-labyrinth/fleurs-trigram-hours0p25-whisper-small-no-language"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id)
FLEURS train + Chichewa Trigrams trainFLEURS dev91399098311305min_duration_seconds=0.0, max_duration_seconds=30.0experiments/whisper_finetune/finetune_whisper.pyopenai/whisper-smalltranscribe--language auto in standalone evaluationnoFalse15001.32The best checkpoint was selected using trainer-side dev evaluation on the duration-filtered FLEURS dev split.
0.56230.15850.7042These values come from the training pipeline and may differ slightly from standalone post-hoc evaluation because the decoding path is not perfectly identical.
Standalone evaluation is recommended for the final release. Filtered and unfiltered results should be reported separately.
min_duration_seconds=0, max_duration_seconds=30transcribeauto| Dataset | Split | Setting | Num examples | WER | CER | Notes |
|---|---|---|---|---|---|---|
| FLEURS | dev | filtered | 305 | 0.5405 | 0.1611 | Filtered to 30 seconds |
| FLEURS | dev | unfiltered | 311 | 0.5341 | 0.1591 | No duration filter |
| FLEURS | test | filtered | 745 | 0.5568 | 0.1661 | Filtered to 30 seconds |
| FLEURS | test | unfiltered | 761 | 0.5531 | 0.1643 | No duration filter |
| Zambezi | dev | filtered | 613 | 0.7157 | 0.2414 | Filtered to 30 seconds |
| Zambezi | dev | unfiltered | 622 | 0.7113 | 0.2384 | No duration filter |
| Zambezi | test | filtered | 427 | 0.6800 | 0.1754 | Filtered to 30 seconds |
| Zambezi | test | unfiltered | 428 | 0.6778 | 0.1746 | No duration filter |
eval/...If you use this checkpoint, please cite:
@misc{fleurs_trigram_hours0p25_whisper_small_no_language_2026,
title = {FLEURS-Trigram Whisper Small No-Language Checkpoint},
author = {AI4Good Labyrinth Team},
year = {2026},
howpublished = {\url{https://huggingface.co/ai4good-labyrinth/fleurs-trigram-hours0p25-whisper-small-no-language}},
note = {Whisper fine-tuning for Chichewa/Nyanja ASR}
}