📄 中文摘要
Cohere推出了一款开源语音模型，旨在为用户提供转录服务。该模型参数相对较少，仅为20亿，适合在消费级GPU上自我托管。它目前支持14种语言，满足了多样化的用户需求，尤其是希望在本地环境中进行语音转录的开发者和企业。此举标志着Cohere在语音技术领域的进一步发展，为用户提供了更多灵活性和选择。
Cohere推出专门用于转录的开源语音模型
📄 English Summary
Cohere launches an open-source voice model specifically for transcription
Cohere has launched an open-source voice model designed specifically for transcription purposes. The model is relatively lightweight, with just 2 billion parameters, making it suitable for self-hosting on consumer-grade GPUs. Currently, it supports 14 languages, catering to a diverse range of user needs, particularly for developers and businesses looking to perform voice transcription in local environments. This move signifies Cohere's further advancement in the voice technology space, offering users greater flexibility and options.