FunAudioLLM/Fun-ASR-MLT-Nano-2512

huggingface.co

Модель automatic-speech-recognition · лицензия apache-2.0

Installation

from transformers import pipeline; pipeline(model="FunAudioLLM/Fun-ASR-MLT-Nano-2512")

Installs into

transformers, python

Not sure where to start — ask an assistant to walk you through:

Specs

Type	Model
Section	Models & platforms / automatic-speech-recognition
Pricing	open source
Platform	Command line
Systems	cli
Hosting	cloud
Install	package
Installs into	transformers, python
Site language	en
Vendor	FunAudioLLM
Views	845
Launched	2025-12-15

Can do

automatic-speech-recognition

Platforms

Tags

en zh ja ko ar multilingual automatic-speech-recognition vllm hi th id vi cs bg ASR ms speech recognition hr tl streaming funasr real-time whisper-alternative end-to-end 31-languages

Found in sources

Similar in «Models & platforms»

Cost-efficient open-source MoE model rivaling GPT-4o in reasoning and math tasks

Open reasoning and coding models on par with the top closed ones.

European open and commercial models, Le Chat and Codestral.

Research faster with Sider AI—summarize web pages, take notes, generate reports, and chat with leading AI models. Powered by ChatGPT, Gemini, Claude, Grok, Deepseek, etc. Try the best AI sidebar now!

The hub of models and datasets: millions of weights, Spaces, Transformers.

Передовая мультимодальная AI-платформа от ByteDance с современными языковыми, визуальными и речевыми моделями, а также интегрированными возможностями рассуждения и поиска.