Hojo-ASR-Multi-V1 开源多语言 ASR 模型发布

开源多语言 ASR 模型 Hojo-ASR-Multi-V1 在 5 种语言上平均 WER 为 3.54，采用声学编码器加 Qwen3-4B 解码器的架构。该模型面向多语言对话语音识别，以 Apache 2.0 许可在 Hugging Face 公开，可通过 hojo-asr Python 包安装并支持本地推理，接受 WAV 路径、音频字节流和 SCP 输入。

正文

An open multilingual ASR model just posted 3.54 average WER across 5 languages

Hojo-ASR-Multi-V1 combines an acoustic encoder with a Qwen3-4B decoder, giving speech recognition an unusually strong language model at the final decoding stage.

Built with a Qwen3-4B LLM decoder
Designed for multilingual conversational speech recognition
Publicly available on Hugging Face, under the Apache 2.0 license
Installable through the hojo-asr Python package
Supports local inference
Accepts WAV file paths, audio byte streams and SCP inputs

There is a bigger technical story behind the 3.54 WER number.

Traditional ASR systems rely heavily on acoustic and language modeling components designed specifically for speech, while Hojo hands the decoding stage to a Qwen3-4B LLM after the audio has been encoded and adapted. So recognition gets access to a much richer model of how words naturally fit together while it is deciding what was actually said.

What makes Hojo even more interesting is that it is reaching that level across multiple languages rather than being built around only 1 language. And it does this with an openly available model that developers can actually run and inspect themselves.

The architecture is probably the most interesting part for me.

Hojo uses an Encoder, Adapter and LLM setup with Qwen3-4B as the decoder, so the final transcript is produced using both acoustic information from the speech and the language knowledge inside the LLM.

That gives the decoder much more context for resolving words that may sound ambiguous from audio alone.

来源：Rohan Paul · x.com

千问 Qwen 语音与音频开源生态模型发布 #模型发布 #语音 #开源生态

在 X 查看原推

AI 评分

AI 评分 47

主题

千问 Qwen 语音与音频开源生态模型发布

Hojo-ASR-Multi-V1 开源多语言 ASR 模型发布

来源

AI 评分

主题

标签