# Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks

DevFeed: [Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks](<https://devfeed.tech/articles/open-asr-leaderboard-trends-and-insights-with-new-multilingual-long-form-tracks-7409.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/open-asr-leaderboard>)

Author: Eric Bezzam; Steven Zheng; Eustache Le Bihan; Vaibhav Srivastav

Published: 2025-11-21T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [asr](<https://devfeed.tech/topics/asr.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>)

Tags: [asr](<https://devfeed.tech/tags/asr.md>), [audio](<https://devfeed.tech/tags/audio.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [inference](<https://devfeed.tech/tags/inference.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [speech](<https://devfeed.tech/tags/speech.md>), [transcription](<https://devfeed.tech/tags/transcription.md>), [trends](<https://devfeed.tech/tags/trends.md>), [whisper](<https://devfeed.tech/tags/whisper.md>)

## AI overview

The Open ASR Leaderboard expands its evaluation with multilingual and long-form transcription tracks. The article highlights accuracy advantages from combining Conformer encoders with LLM decoders, throughput advantages from CTC and TDT decoders, Whisper as a multilingual baseline, and the effects of fine-tuning on specialized performance.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.