datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MMAU
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset mmau-test-mini --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/MMAU.KeSpeech
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset KeSpeech --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/KeSpeech.VoxCeleb
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset voxceleb1 --model gpt4o_audio
python audio_evals/main.py --dataset voxceleb2 --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/VoxCeleb.WenetSpeech
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset WenetSpeech-test-meeting --model gpt4o_audio
python audio_evals/main.py --dataset WenetSpeech-test-net --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/WenetSpeech.librispeech
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset librispeech-test-clean --model gpt4o_audio
python audio_evals/main.py --dataset librispeech-dev-clean --model gpt4o_audio
python audio_evals/main.py --dataset librispeech-test-other --model gpt4o_audio
python audio_evals/main.py --dataset librispeech-dev-other --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/librispeech.AISHELL-1
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset aishell-1 --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/AISHELL-1.llama-questions
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset llama-questions --model gpt4o_speech
python audio_evals/main.py --dataset llama-questions-s2t --model gpt4o_speech
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/llama-questions.AudioCaps
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset audiocaps --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/AudioCaps.wavcaps-audioset
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset wavcaps-audioset --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/wavcaps-audioset.RespiratorySound
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset respiratory-crackles --model gpt4o_audio
python audio_evals/main.py --dataset respiratory-wheezes --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/RespiratorySound.speech-CMMLUThis dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
Usage
python audio_evals/main.py --dataset speech-cmmlu --model MiniCPMo2_6-speech --use_model_pool --workers 2
@article{ultraevalaudio,
title={UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models},
author={Qundong Shi and Jie Zhou and Biyuan Lin and Junbo Cui and Guoyang Zeng and Yixuan Zhou and… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/speech-CMMLU.Seed-TTS-Evaltedlium
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset tedlium-release1 --model gpt4o_audio
python audio_evals/main.py --dataset tedlium-release2 --model gpt4o_audio
python audio_evals/main.py --dataset tedlium-release3 --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/tedlium.peoples_speech
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset peoples-speech --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/peoples_speech.wavcaps-freesound
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset wavcaps-freesound --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/wavcaps-freesound.facebook_multilingual_librispeech
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset mls_dutch --model gpt4o_audio
python audio_evals/main.py --dataset mls_french --model gpt4o_audio
python audio_evals/main.py --dataset mls_german --model gpt4o_audio
python audio_evals/main.py --dataset mls_italian --model gpt4o_audio
python audio_evals/main.py --dataset mls_polish --model gpt4o_audio
python… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/facebook_multilingual_librispeech.speech-web-questions
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset speech-web-questions --model gpt4o_speech
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/speech-web-questions.ClothoAQA
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset clotho-aqa-sample --model gpt4o_audio
python audio_evals/main.py --dataset clotho-aqa --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/ClothoAQA.speech-HSKRAVDESS
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset ravdess-emo --model gpt4o_audio
python audio_evals/main.py --dataset ravdess-gender --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/RAVDESS.audio-MNIST
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset audio-MNIST --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/audio-MNIST.speech-triavia-qa
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset speech-triviaqa --model gpt4o_speech
python audio_evals/main.py --dataset speech-triviaqa-s2t --model gpt4o_speech
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/speech-triavia-qa.wavcaps-soundbible
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset wavcaps-soundbible --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/wavcaps-soundbible.CommonVoice_15
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset cv-15-en --model gpt4o_audio
python audio_evals/main.py --dataset cv-15-zh --model gpt4o_audio
python audio_evals/main.py --dataset cv-15-fr --model gpt4o_audio
python audio_evals/main.py --dataset cv-15-yue --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/CommonVoice_15.DESEDpublic_eval
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset desed --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/DESEDpublic_eval.vocalsound
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset vocalsound --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/vocalsound.MELD
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset meld-emo --model gpt4o_audio
python audio_evals/main.py --dataset meld-sentiment --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/MELD.TwinkStartpython audio_evals/main.py --dataset nsynth --model gpt4o_audio
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器 ⚙️:无需再四处搜寻评估工具,UltraEval-Audio内置八种常用的评估方法(如WER、WER-ZH、BLEU、G-Eval),无论是基于规则还是模型驱动,都能满足您的需求。
功能强大,灵活易用 🛠️:支持预览测试、随机样本、错误重试、断点重跑等功能,确保评估过程灵活可控,提升效率与准确性。
无缝集成自定义数据集… See the full description on the dataset page: https://huggingface.co/datasets/Samoristian/TwinkStart.air-chat
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/UltraEval/UltraEval-Audio) framework.
UltraEval-Audio: 🎙️ Open-Source Speech Model Evaluation Framework, Empowering Your AI Voice Research!
One-Stop Evaluation, Time-Saving and Effortless! 🚀
UltraEval-Audio integrates 30+ benchmarks, covering speech, sound, medicine, music four major domains, supporting 10 languages, and encompassing 12 types of tasks, helping… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/air-chat.speech-chatbot-alpaca-eval
This dataset only contains test data, which is integrated into UltraEval-Audio(https://github.com/OpenBMB/UltraEval-Audio) framework.
python audio_evals/main.py --dataset speech-chatbot-alpaca-eval --model gpt4o_speech
🚀超凡体验,尽在UltraEval-Audio🚀
UltraEval-Audio——全球首个同时支持语音理解和语音生成评估的开源框架,专为语音大模型评估打造,集合了34项权威Benchmark,覆盖语音、声音、医疗及音乐四大领域,支持十种语言,涵盖十二类任务。选择UltraEval-Audio,您将体验到前所未有的便捷与高效:
一键式基准管理 📥:告别繁琐的手动下载与数据处理,UltraEval-Audio为您自动化完成这一切,轻松获取所需基准测试数据。
内置评估利器… See the full description on the dataset page: https://huggingface.co/datasets/TwinkStart/speech-chatbot-alpaca-eval.
