Boson AI 发布 Qwen3-ASR-1.7B-hf-beam4，优化解码提升语音识别性能

Boson AI bosonai/Qwen3-ASR-1.7B-hf-beam4 bosonai/Qwen3-ASR-1.7B-hf-beam4 https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4

bosonai/Qwen3-ASR-1.7B-hf-beam4 · Hugging Face Hugging Face (https://huggingface.co/) Models (https://huggingface.co/models) Datasets (https://huggingface.co/datasets) Spaces (https://huggingface.co/spaces) Buckets new (https://huggingface.co/storage) Docs (https://huggingface.co/docs) Enterprise (https://huggingface.co/enterprise) Pricing (https://huggingface.co/pricing) Website Tasks (https://huggingface.co/tasks) HuggingChat (https://huggingface.co/chat) Collections (https://huggingface.co/collections) Languages (https://huggingface.co/languages) Organizations (https://huggingface.co/organizations) Community Blog (https://huggingface.co/blog) Posts (https://huggingface.co/posts) Daily Papers (https://huggingface.co/papers) Hardware (https://huggingface.co/hardware) Learn (https://huggingface.co/learn) Discord (https://huggingface.co/join/discord) Forum (https://discuss.huggingface.co/) GitHub (https://github.com/huggingface) Solutions Team & Enterprise (https://huggingface.co/enterprise) Hugging Face PRO (https://huggingface.co/pro) Enterprise Support (https://huggingface.co/support) Inference Providers (https://huggingface.co/inference/models) Inference Endpoints (https://huggingface.co/inference-endpoints) Storage Buckets (https://huggingface.co/storage) Log In (https://huggingface.co/login) Sign Up (https://huggingface.co/join) (https://huggingface.co/bosonai) bosonai (https://huggingface.co/bosonai) / Qwen3-ASR-1.7B-hf-beam4 (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4) like 2 Follow Boson AI 657 Automatic Speech Recognition (https://huggingface.co/models?pipeline_tag=automatic-speech-recognition) Transformers (https://huggingface.co/models?library=transformers) Safetensors (https://huggingface.co/models?library=safetensors) English (https://huggingface.co/models?language=en) qwen3_asr (https://huggingface.co/models?other=qwen3_asr) asr (https://huggingface.co/models?other=asr) qwen3-asr (https://huggingface.co/models?other=qwen3-asr) open-asr-leaderboard (https://huggingface.co/models?other=open-asr-leaderboard) License: apache-2.0 Model card (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4) Files Files and versions xet (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4/tree/main) Community (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4/discussions) Deploy Copy to bucket new Use this model Instructions to use bosonai/Qwen3-ASR-1.7B-hf-beam4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started. Libraries Transformers (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4?library=transformers) How to use bosonai/Qwen3-ASR-1.7B-hf-beam4 with Transformers: # Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bosonai/Qwen3-ASR-1.7B-hf-beam4") # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("bosonai/Qwen3-ASR-1.7B-hf-beam4") model = AutoModelForMultimodalLM.from_pretrained("bosonai/Qwen3-ASR-1.7B-hf-beam4", device_map="auto") Notebooks Google Colab (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4/colab) Kaggle (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4/kaggle) Qwen3-ASR 1.7B HF — beam-4 (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4#qwen3-asr-17b-hf--beam-4) Evaluation (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4#evaluation) Usage (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4#usage) Provenance (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4#provenance) (https://huggingface.co/bosonai/Qwen3-ASR-1.7B-hf-beam4#qwen3-asr-17b-hf--beam-4) Qwen3-ASR 1.7B HF — beam-4 This is a decoding-calibrated derivative of Qwen/Qwen3-ASR-1.7B-hf (https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf) . The model weights and processor are unchanged. The only inference change is num_beams: 4 in generation_con