{"benchmark_id":"common-voice-15","benchmark_name":"Common Voice 15","benchmark_description":"Common Voice is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Version 15.0 contains 28,750 recorded hours across 114 languages, consisting of crowdsourced voice recordings with corresponding transcriptions.","max_score":100.0,"categories":["language","speech_to_text","audio"],"modality":"audio","total_models":1,"entries":[{"rank":1,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.076,"normalized_score":0.076,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-03-27","announcement_date":"2025-03-27","multimodal":true,"param_count":7000000000,"is_new":false}]}