美通社

2024-09-23 14:00

Jingzhunxue debuts world's first open-source, end-to-end and education-focused speech LLM FlowMirror

Hangzhou-based AI startup looks to set new standards in AI-driven educational assistance

HANGZHOU, China, Sept. 23, 2024 /PRNewswire/ -- Jingzhunxue, a Hangzhou-based education technology company, has launched "FlowMirror-s(V02)," the world's first open-source end-to-end large language model (LLM) for speech detection and interaction catering to the education industry, marking the company's endeavor to promote industry knowledge-sharing and the adoption of AI-powered learning services.

In a departure from traditional Automatic Speech Recognition and Text-to-Speech processes, "FlowMirror-s(V02)" is built from the ground up using a self-supervised Chinese speech codec system, with its weight initialized based on a text LLM.

The result is a model trained end-to-end on speech and dialogue data, allowing for low-latency, end-to-end speech interactions.

Jingzhunxue has also developed the world's first "Hyper-Realistic AI One-on-One Tutor" using its FlowMirror-s(V02) model. Designed under the "AI Native" principle, this AI tutor closely mimics real teachers, offering personalized, systemized instruction that surpasses traditional AI tools and extends across all scenarios.

"We focus especially on educational applications. Hopefully, the success of this model will not only drive innovation in the Chinese AI community but also advance the education sector," says Renbin Yang, founder and CEO of Jingzhunxue. "This is our cornerstone step toward intelligent learning assistance."

By leveraging Alibaba's LLM Tongyi Qianwen (Qwen), FlowMirror stands as one of China's most advanced educational models. Powered by Qwen's trillion-parameter framework and trained using the multi-GPU Bailian platform from AliCloud, FlowMirror offers a range of specialized features.

It incorporates over 2 billion proprietary tokens through a sophisticated data pipeline designed for educational assistance. It achieves multimodal interaction by integrating Alibaba's visual model, enabling dynamic problem-solving and tutoring support.

The model can detect over 40 emotional and physical states through voice and visual cues. Besides, thanks to 160,000 hours of educational speech training, it aligns its speech patterns with those of human teachers.

Jingzhunxue's Bong series e-learning tablet
Jingzhunxue's Bong series e-learning tablet

Additionally, FlowMirror offers personalized teaching styles inspired by renowned educators and utilizes virtual teacher technology to generate exclusive, high-definition, real-time interactions from just one hour of video data. Moreover, its knowledge graph draws on millions of data sets extracted from an extensive question bank and learning data pool to master various educational materials.

FlowMirror-s v0.1 and v0.2 were pre-trained on 20,000 and 50,000 hours of speech data, respectively, validating the model's end-to-end speech capabilities and scalability.

The latest version, "FlowMirror-s(v0.2)," facilitates seamless speech input-to-output interactions, making it better-suited to educational scenarios with natural, real teacher-like dialogues. Jingzhunxue plans to showcase its technology's practical applications soon.

In May, Jingzhunxue secured nearly RMB 200 million ($28 million) in a funding round backed solely by Alibaba. The proceeds will be used to develop and promote its AI Native educational devices, such as the Bong series e-learning tablets, now available on e-commerce platforms like Tmall and JD.com.

FlowMirror-s is accessible via GitHub:

https://github.com/Zhejiang-Jingzhunxue/flow_mirror

About Jingzhunxue

Backed by Alibaba, Jingzhunxue specializes in integrating AI software and hardware solutions tailored to the education industry. The company aims to provide AI-driven learning experiences that rival or surpass human instruction, while also making these technologies affordable for all.

source: Jingzhunxue

【你點睇?】特朗普當局擬關閉美國國家民主基金會,你認為若其關閉是否可促進全球和平穩定?► 立即投票

人氣文章
最近7天
1
PapaHome淘寶家具實體店22日開幕,選址尖沙咀中港城,料創100個就業機會
2
高息定存 | 一周高息合集,蛇年定存金蛇起舞,1個月定存高達8厘
3
港股 | 午市前瞻 | AI應用概念炒作有錢途 下階段部署邊隻好?
4
日入而息 | 習近平據報下周見科企領袖,證監會審視8券商孖展風控,大酒店轉蝕9億
5
高息定存 | 信銀國際12個月港元定存高達3.5厘
6
彭博亞洲20大富裕家族,香港5大家族上榜,新地郭氏排名最高,無李嘉誠李兆基?
7
David Webb:因病情惡化,將有序結束個人財經網站
8
港股 | 蕭猷華:恒指短線回調,中線繼續看好
9
iPhone SE 4或於本周內上架官網
10
AI | 蔡崇信確認阿里與蘋果合作,撰文談DeepSeek崛起帶來兩大啟示
1
港股 | 蕭猷華:內地AI發展迅速,阿里巴巴股價看俏
2
高息定存 | 一周高息合集,銀行高息搶存,富邦1個月4.88厘,華僑1年期3.6厘
3
PapaHome淘寶家具實體店22日開幕,選址尖沙咀中港城,料創100個就業機會
4
英偉達 | DeepSeek衝擊AI晶片行業結構 英偉達暴跌仍未急抄底
5
高息定存 | 華僑銀行推新春港元定存優惠,88天或188天享3.68厘
6
啟德體育園明天足球賽測試,4.4萬公僕參與涉逾400萬車馬費
7
高息定存 | 花旗3個月港元定存息加至4厘,信銀國際3.88厘
8
環球央行 | 歐洲央行宣布再次減息0.25厘,符合市場預期
9
一本萬利 | 2025年的五個「勿」(有片)
10
電騙 | 黃俊碩:多管齊下,防治內地留學生受騙
11
高息定存 | 一周高息合集,蛇年定存金蛇起舞,1個月定存高達8厘
12
易經看世界 | 乙巳蛇年趨吉五招:言行注意甚麼?應遠離甚麼人?(有片)
13
專訪 | 關稅戰 | 香港物流協會副會長梁庭彰:美物流商停收包裹對跨境電商打擊重大
14
港股 | 午市前瞻 | iPhone SE難救中國市場 專家提醒比電已超買
15
洪灝專訪 | 淘寶衝擊巨大,港樓價未反映大周期拐點(有片)
16
【FOCUS】螺絲殼裏做道場,DeepSeek致勝啟示
17
專訪|洪灝:美股更大跌幅在前面,恐需習慣4%通脹(有片)
18
習近平應約與特朗普通電話,特:冀盡快與習見面
19
大S | 台灣藝人徐熙媛因流感併發肺炎逝世,享年48歲
20
新世界 | 摩通:新世界若債務違約或打開行業「潘朵拉盒子」
21
DeepSeek推出即上蘋果中國區榜首,能力直追OpenAI
22
收市短打 | 楊韻銳:港股升勢有成交配合 惟留意關鍵阻力位!
23
高息定存 | 一周高息合集,部分銀行逆市加息,南商3個月加至3.8厘
24
港股 | 蕭猷華:春節假後,恒指逐步上望21000點
25
馬斯克明拆特朗普台,指其星際之門計劃「假大空」
26
特朗普就職 | 特朗普上台後行動列表
27
【FOCUS】侵侵呼籲全球「降息」,日銀祭18年最激進加息
28
港股 | 午市前瞻 | AI應用概念炒作有錢途 下階段部署邊隻好?
29
神州經脈 | 特朗普或與華討論關稅,人民幣大漲,滬指連升兩周
30
高息定存 | 富邦一周港元定存高達9.88厘,一個月4.88厘
專業版
HV2
精裝版
SV2
串流版
IQ 登入
強化版
TQ
強化版
MQ

【etnet 30周年】多重慶祝活動一浪接一浪,好禮連環賞!

【蛇年行大運 新年好賞「飾」】etnet賞太歲開運趨吉避凶神器

etnet榮獲HKEX Awards 2023 「最佳證券數據供應商」大獎

貨幣攻略

大國博弈

說說心理話

Watch Trends 2024

北上食買玩

Art Month 2024

理財秘笈

流感高峰期

山今養生智慧

輕鬆護老