├── README.md ├── README_CN.md ├── assets ├── framework.png ├── logo.png └── radar_compare_qwen_audio.png ├── demo ├── demo.sh ├── requirements_web_demo.txt └── web_demo_audio.py ├── eval_audio ├── EVALUATION.md ├── cn_tn.py ├── evaluate_asr.py ├── evaluate_chat.py ├── evaluate_emotion.py ├── evaluate_st.py ├── evaluate_tokenizer.py ├── evaluate_vocal_sound.py └── whisper_normalizer │ ├── basic.py │ ├── english.json │ └── english.py └── finetune ├── accelerate_configs ├── deepspeed_z1.yaml ├── deepspeed_z2.yaml └── deepspeed_z3.yaml ├── run.py └── run.sh /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/README.md -------------------------------------------------------------------------------- /README_CN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/README_CN.md -------------------------------------------------------------------------------- /assets/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/assets/framework.png -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/assets/logo.png -------------------------------------------------------------------------------- /assets/radar_compare_qwen_audio.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/assets/radar_compare_qwen_audio.png -------------------------------------------------------------------------------- /demo/demo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/demo/demo.sh -------------------------------------------------------------------------------- /demo/requirements_web_demo.txt: -------------------------------------------------------------------------------- 1 | gradio==4.31.3 2 | modelscope-studio -------------------------------------------------------------------------------- /demo/web_demo_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/demo/web_demo_audio.py -------------------------------------------------------------------------------- /eval_audio/EVALUATION.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/EVALUATION.md -------------------------------------------------------------------------------- /eval_audio/cn_tn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/cn_tn.py -------------------------------------------------------------------------------- /eval_audio/evaluate_asr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_asr.py -------------------------------------------------------------------------------- /eval_audio/evaluate_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_chat.py -------------------------------------------------------------------------------- /eval_audio/evaluate_emotion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_emotion.py -------------------------------------------------------------------------------- /eval_audio/evaluate_st.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_st.py -------------------------------------------------------------------------------- /eval_audio/evaluate_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_tokenizer.py -------------------------------------------------------------------------------- /eval_audio/evaluate_vocal_sound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/evaluate_vocal_sound.py -------------------------------------------------------------------------------- /eval_audio/whisper_normalizer/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/whisper_normalizer/basic.py -------------------------------------------------------------------------------- /eval_audio/whisper_normalizer/english.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/whisper_normalizer/english.json -------------------------------------------------------------------------------- /eval_audio/whisper_normalizer/english.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/eval_audio/whisper_normalizer/english.py -------------------------------------------------------------------------------- /finetune/accelerate_configs/deepspeed_z1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/finetune/accelerate_configs/deepspeed_z1.yaml -------------------------------------------------------------------------------- /finetune/accelerate_configs/deepspeed_z2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/finetune/accelerate_configs/deepspeed_z2.yaml -------------------------------------------------------------------------------- /finetune/accelerate_configs/deepspeed_z3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/finetune/accelerate_configs/deepspeed_z3.yaml -------------------------------------------------------------------------------- /finetune/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/finetune/run.py -------------------------------------------------------------------------------- /finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lollipop/Qwen2-Audio/HEAD/finetune/run.sh --------------------------------------------------------------------------------