zhifu gao

langgz's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in funasr/paraformer-en 16 days ago

docs: make Paraformer-en model card directly usable

#2 opened 16 days ago by

langgz

New activity in funasr/paraformer-zh-streaming 16 days ago

docs: add immutable Apache-2.0 license snapshot

1

#1 opened 16 days ago by

langgz

New activity in FunAudioLLM/Paraformer-GGUF 24 days ago

docs: link the deployment product hub

1

#1 opened 24 days ago by

langgz

New activity in FunAudioLLM/Fun-ASR-Nano-GGUF 24 days ago

docs: link the deployment product hub

1

#2 opened 24 days ago by

langgz

New activity in FunAudioLLM/FunClip 26 days ago

FunClip v2.1.0: reproducible source release and bilingual guides

#3 opened 26 days ago by

langgz

New activity in FunAudioLLM/Fun-ASR-MLT-Nano-2512 about 1 month ago

docs: require current FunASR release in examples

1

#5 opened about 1 month ago by

langgz

New activity in FunAudioLLM/Fun-ASR-Nano-GGUF about 1 month ago

Link model card to FunAudioLLM paper

1

#1 opened about 1 month ago by

langgz

New activity in FunAudioLLM/Fun-ASR-Nano-2512-hf about 1 month ago

Link model card to FunAudioLLM paper

1

#3 opened about 1 month ago by

langgz

Refresh checkpoint for shared Whisper component layout

2

#2 opened about 1 month ago by

langgz

New activity in FunAudioLLM/FunClip about 1 month ago

build: pin Space to Python 3.12

#2 opened about 1 month ago by

langgz

docs: align Space copy with deployed workflow

#1 opened about 1 month ago by

langgz

New activity in FunAudioLLM/Fun-ASR-Nano-2512-hf about 1 month ago

docs: clarify Nano language coverage

1

#1 opened about 1 month ago by

langgz

New activity in FunAudioLLM/Fun-ASR-MLT-Nano-2512 about 1 month ago

权重问题

2

#2 opened 8 months ago by

wjfwjf

Model outputs Japanese text even when English is specified

3

#4 opened 7 months ago by

jerryyoon

Improve model card: Add metadata, paper link, code link, and project page link

1

#3 opened 8 months ago by

nielsr

New activity in emotion2vec/emotion2vec_plus_large 3 months ago

All-in-one alternative: SenseVoice does ASR + Emotion in a single model

#1 opened 3 months ago by

langgz

New activity in openai/whisper-small 3 months ago

Faster + more accurate alternative: FunASR SenseVoice (234MB, 170x realtime)

#50 opened 3 months ago by

langgz

New activity in Qwen/Qwen3-ASR-1.7B 3 months ago

Use Qwen3-ASR with FunASR toolkit (one-line setup, speaker diarization)

👍🔥 2

#24 opened 3 months ago by

langgz

New activity in openai/whisper-large-v3-turbo 3 months ago

Even faster alternative: FunASR SenseVoice (170x realtime, CPU-friendly)

#90 opened 3 months ago by

langgz

New activity in openai/whisper-large-v3 3 months ago

Benchmark: FunASR 170x realtime vs Whisper 13x — non-autoregressive alternative

#233 opened 3 months ago by

langgz