norbertm/whisper-eval-rare-languages-csv

Domaine:

natural language processing

Type de record:

dataset

Créateur:

nor

Hôte:

This enhanced dataset contains comprehensive evaluation results of OpenAI's Whisper 3 Large model on rare languages from Mozilla Common Voice 17, with extensive additional metrics for thorough ASR evaluation. Enhanced Error Metrics: WER (Word Error Rate): Standard word-level error measurement

SunbirdAI/kinyarwanda-whisper-eval

Evaluating Whisper performance wrt hours of labelled kinyarwanda audio # Kinyarwanda Whisper Evalua

EbunoluwaArimoro/whisper-yoruba-asr-eval

# Whisper on Yorùbá — an ASR evaluation Evaluating OpenAI Whisper `large-v3` on Yorùbá speech using

zainmouhamed456-hub/whisper-pulaar-eval

Google Colab-ready Pulaar evaluation pipeline for fine-tuned Whisper models # Whisper Pulaar Eval

Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages

Unsupervised translation has reached impressive performance on resource-rich language pairs such as

flavnat/csv-parse

Java application designed to read and process CSV files containing Amharic text. It provides functio

SM_Survey_UPSA-2020.csv

This data was collected through an online survey at the University of Professional Studies Accra(UPS

norbertm/whisper-eval-rare-languages-csv

Domaine:

Type de record:

Visit

Tasks

Languages