├── FAQ.md ├── FAQ_zh.md ├── LICENSE ├── NOTICE ├── README.md ├── README_CN.md ├── TUTORIAL.md ├── TUTORIAL_zh.md ├── assets ├── .DS_Store ├── audio │ ├── 1089_134686_000007_000004.wav │ ├── 1089_134686_000007_000004_companionless.wav │ ├── 1089_134686_000007_000004_person_name.wav │ ├── 1272-128104-0000-middle_classes.wav │ ├── 1272-128104-0000.flac │ ├── es.mp3 │ ├── example-重庆话.wav │ ├── glass-breaking-151256.mp3 │ ├── music.wav │ ├── out.wav │ ├── 你没事吧-消极.wav │ └── 你没事吧-轻松.wav ├── audio_logo.jpg ├── evaluation.png ├── framework.png ├── logo.jpg ├── logo.png ├── radar_new.png ├── sft_sample.txt └── wechat.png ├── audio.py ├── base_generation_config.json ├── chat_generation_config.json ├── config.json ├── configuration_qwen.py ├── eval_audio ├── EVALUATION.md ├── evaluate_aqa.py ├── evaluate_asr.py ├── evaluate_caption.py ├── evaluate_emotion.py ├── evaluate_note_analysis.py ├── evaluate_scene.py ├── evaluate_srwt.py ├── evaluate_st.py ├── evaluate_tokenizer.py ├── evaluate_vocal_sound.py ├── heareval_score.py └── metrics.py ├── mel_filters.npz ├── modeling_qwen.py ├── qwen.tiktoken ├── qwen_generation_utils.py ├── requirements.txt ├── requirements_web_demo.txt ├── tokenization_qwen.py ├── tokenizer_config.json ├── utils.py ├── web_demo_audio.py └── wechat.png /FAQ.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/FAQ.md -------------------------------------------------------------------------------- /FAQ_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/FAQ_zh.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/LICENSE -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/NOTICE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/README.md -------------------------------------------------------------------------------- /README_CN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/README_CN.md -------------------------------------------------------------------------------- /TUTORIAL.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/TUTORIAL.md -------------------------------------------------------------------------------- /TUTORIAL_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/TUTORIAL_zh.md -------------------------------------------------------------------------------- /assets/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/.DS_Store -------------------------------------------------------------------------------- /assets/audio/1089_134686_000007_000004.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/1089_134686_000007_000004.wav -------------------------------------------------------------------------------- /assets/audio/1089_134686_000007_000004_companionless.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/1089_134686_000007_000004_companionless.wav -------------------------------------------------------------------------------- /assets/audio/1089_134686_000007_000004_person_name.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/1089_134686_000007_000004_person_name.wav -------------------------------------------------------------------------------- /assets/audio/1272-128104-0000-middle_classes.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/1272-128104-0000-middle_classes.wav -------------------------------------------------------------------------------- /assets/audio/1272-128104-0000.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/1272-128104-0000.flac -------------------------------------------------------------------------------- /assets/audio/es.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/es.mp3 -------------------------------------------------------------------------------- /assets/audio/example-重庆话.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/example-重庆话.wav -------------------------------------------------------------------------------- /assets/audio/glass-breaking-151256.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/glass-breaking-151256.mp3 -------------------------------------------------------------------------------- /assets/audio/music.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/music.wav -------------------------------------------------------------------------------- /assets/audio/out.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/out.wav -------------------------------------------------------------------------------- /assets/audio/你没事吧-消极.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/你没事吧-消极.wav -------------------------------------------------------------------------------- /assets/audio/你没事吧-轻松.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio/你没事吧-轻松.wav -------------------------------------------------------------------------------- /assets/audio_logo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/audio_logo.jpg -------------------------------------------------------------------------------- /assets/evaluation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/evaluation.png -------------------------------------------------------------------------------- /assets/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/framework.png -------------------------------------------------------------------------------- /assets/logo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/logo.jpg -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/logo.png -------------------------------------------------------------------------------- /assets/radar_new.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/radar_new.png -------------------------------------------------------------------------------- /assets/sft_sample.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/sft_sample.txt -------------------------------------------------------------------------------- /assets/wechat.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/assets/wechat.png -------------------------------------------------------------------------------- /audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/audio.py -------------------------------------------------------------------------------- /base_generation_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/base_generation_config.json -------------------------------------------------------------------------------- /chat_generation_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/chat_generation_config.json -------------------------------------------------------------------------------- /config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/config.json -------------------------------------------------------------------------------- /configuration_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/configuration_qwen.py -------------------------------------------------------------------------------- /eval_audio/EVALUATION.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/EVALUATION.md -------------------------------------------------------------------------------- /eval_audio/evaluate_aqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_aqa.py -------------------------------------------------------------------------------- /eval_audio/evaluate_asr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_asr.py -------------------------------------------------------------------------------- /eval_audio/evaluate_caption.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_caption.py -------------------------------------------------------------------------------- /eval_audio/evaluate_emotion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_emotion.py -------------------------------------------------------------------------------- /eval_audio/evaluate_note_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_note_analysis.py -------------------------------------------------------------------------------- /eval_audio/evaluate_scene.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_scene.py -------------------------------------------------------------------------------- /eval_audio/evaluate_srwt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_srwt.py -------------------------------------------------------------------------------- /eval_audio/evaluate_st.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_st.py -------------------------------------------------------------------------------- /eval_audio/evaluate_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_tokenizer.py -------------------------------------------------------------------------------- /eval_audio/evaluate_vocal_sound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/evaluate_vocal_sound.py -------------------------------------------------------------------------------- /eval_audio/heareval_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/heareval_score.py -------------------------------------------------------------------------------- /eval_audio/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/eval_audio/metrics.py -------------------------------------------------------------------------------- /mel_filters.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/mel_filters.npz -------------------------------------------------------------------------------- /modeling_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/modeling_qwen.py -------------------------------------------------------------------------------- /qwen.tiktoken: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/qwen.tiktoken -------------------------------------------------------------------------------- /qwen_generation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/qwen_generation_utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/requirements.txt -------------------------------------------------------------------------------- /requirements_web_demo.txt: -------------------------------------------------------------------------------- 1 | gradio==3.39.0 2 | -------------------------------------------------------------------------------- /tokenization_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/tokenization_qwen.py -------------------------------------------------------------------------------- /tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/tokenizer_config.json -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/utils.py -------------------------------------------------------------------------------- /web_demo_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/web_demo_audio.py -------------------------------------------------------------------------------- /wechat.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/QwenLM/Qwen-Audio/HEAD/wechat.png --------------------------------------------------------------------------------