Duplicate from ASLP-lab/WSChuan-ASR

Co-authored-by: ASLP-lab <ASLP-lab@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Omni-3B-Chuan/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Paraformer-large-Chuan/am.mvn

@@ -0,0 +1,8 @@
+<Nnet> 
+<Splice> 560 560
+[ 0 ]
+<AddShift> 560 560 
+<LearnRateCoef> 0 [ -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 ]
+<Rescale> 560 560
+<LearnRateCoef> 0 [ 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 ]
+</Nnet> 

Paraformer-large-Chuan/config.yaml

@@ -0,0 +1,126 @@
+model: Paraformer
+model_conf:
+  ctc_weight: 0.0
+  lsm_weight: 0.1
+  length_normalized_loss: true
+  predictor_weight: 1.0
+  predictor_bias: 1
+  sampling_ratio: 0.75
+encoder: SANMEncoder
+encoder_conf:
+  output_size: 512
+  attention_heads: 4
+  linear_units: 2048
+  num_blocks: 50
+  dropout_rate: 0.1
+  positional_dropout_rate: 0.1
+  attention_dropout_rate: 0.1
+  input_layer: pe
+  pos_enc_class: SinusoidalPositionEncoder
+  normalize_before: true
+  kernel_size: 11
+  sanm_shfit: 0
+  selfattention_layer_type: sanm
+decoder: ParaformerSANMDecoder
+decoder_conf:
+  attention_heads: 4
+  linear_units: 2048
+  num_blocks: 16
+  dropout_rate: 0.1
+  positional_dropout_rate: 0.1
+  self_attention_dropout_rate: 0.1
+  src_attention_dropout_rate: 0.1
+  att_layer_num: 16
+  kernel_size: 11
+  sanm_shfit: 0
+predictor: CifPredictorV2
+predictor_conf:
+  idim: 512
+  threshold: 1.0
+  l_order: 1
+  r_order: 1
+  tail_threshold: 0.45
+frontend: WavFrontend
+frontend_conf:
+  fs: 16000
+  window: hamming
+  n_mels: 80
+  frame_length: 25
+  frame_shift: 10
+  lfr_m: 7
+  lfr_n: 6
+  cmvn_file: ./speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/am.mvn
+specaug: SpecAugLFR
+specaug_conf:
+  apply_time_warp: false
+  time_warp_window: 5
+  time_warp_mode: bicubic
+  apply_freq_mask: true
+  freq_mask_width_range:
+  - 0
+  - 30
+  lfr_rate: 6
+  num_freq_mask: 1
+  apply_time_mask: true
+  time_mask_width_range:
+  - 0
+  - 12
+  num_time_mask: 1
+train_conf:
+  accum_grad: 1
+  grad_clip: 5
+  max_epoch: 5
+  val_scheduler_criterion:
+  - valid
+  - acc
+  best_model_criterion:
+  - - valid
+    - acc
+    - max
+  keep_nbest_models: 100
+  log_interval: 500
+  resume: true
+  validate_interval: 5000
+  save_checkpoint_interval: 5000
+  avg_nbest_model: 10
+  use_deepspeed: false
+  deepspeed_config: ./config/ds_stage1.json
+optim: adam
+optim_conf:
+  lr: 0.0002
+scheduler: warmuplr
+scheduler_conf:
+  warmup_steps: 30000
+dataset: AudioDataset
+dataset_conf:
+  index_ds: IndexDSJsonl
+  batch_sampler: BatchSampler
+  batch_type: token
+  batch_size: 300
+  max_token_length: 2048
+  buffer_size: 500
+  shuffle: true
+  num_workers: 4
+  data_split_num: 1
+  sort_size: 1024
+tokenizer: CharTokenizer
+tokenizer_conf:
+  unk_symbol: <unk>
+  split_with_space: true
+  token_list: ./speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.json
+  seg_dict_file: ./speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/seg_dict
+input_size: 560
+ctc_conf:
+  dropout_rate: 0.0
+  ctc_type: builtin
+  reduce: true
+  ignore_nan_grad: true
+normalize: null
+init_param: /home/work_nfs9/sywang/code/paraformer/outputs/model.pt
+config: /home/work_nfs9/sywang/code/paraformer/outputs/config.yaml
+is_training: true
+train_data_set_list: data/train.jsonl
+valid_data_set_list: data/val.jsonl
+output_dir: ./outputs
+model_path: /home/work_nfs9/sywang/code/paraformer/outputs
+device: cpu

Paraformer-large-Chuan/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb8f6c514ada6029c3504f6629a4756a583fe801e56a383a095636dc4c3ee77
+size 2642208221

Qwen2.5-Omni-3B-Chuan/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|AUDIO|>": 151646,
+  "<|IMAGE|>": 151655,
+  "<|VIDEO|>": 151656,
+  "<|audio_bos|>": 151647,
+  "<|audio_eos|>": 151648,
+  "<|box_end|>": 151649,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|vision_bos|>": 151652,
+  "<|vision_eos|>": 151653,
+  "<|vision_pad|>": 151654
+}

Qwen2.5-Omni-3B-Chuan/args.json

@@ -0,0 +1,373 @@
+{
+  "output_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 2,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 5.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 2000.0,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": 42,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": 2000.0,
+  "dataloader_num_workers": 4,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
+  "disable_tqdm": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "deepspeed": {
+    "fp16": {
+      "enabled": "auto",
+      "loss_scale": 0,
+      "loss_scale_window": 1000,
+      "initial_scale_power": 16,
+      "hysteresis": 2,
+      "min_loss_scale": 1
+    },
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 2,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "allgather_partitions": true,
+      "allgather_bucket_size": 200000000.0,
+      "overlap_comm": false,
+      "reduce_scatter": true,
+      "reduce_bucket_size": 200000000.0,
+      "contiguous_gradients": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "hub_revision": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 18000000,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": null,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "metric": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "use_flash_ckpt": false,
+  "model": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
+  "model_type": "qwen2_5_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "flash_attn",
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen2_5_omni",
+  "system": "You are a speech recognition model.",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": false,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "data/train/train_chuan2.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "lazy_tokenize": true,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_lark_webhook_url": null,
+  "swanlab_lark_secret": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "early_stop_interval": null,
+  "rank": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen2.5-Omni-3B",
+  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fe20f5868e0>, model_arch=MultiModelKeys(arch_name='qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "model_dir": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2000, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='lora', local_repo_path=None, galore_config=None)"
+}

Qwen2.5-Omni-3B-Chuan/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

Qwen2.5-Omni-3B-Chuan/config.json

@@ -0,0 +1,644 @@
+{
+  "architectures": [
+    "Qwen2_5OmniForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "enable_audio_output": true,
+  "enable_talker": true,
+  "hidden_size": 2048,
+  "keys_to_ignore_at_inference": [
+    "past_key_values",
+    "hidden_states",
+    "attention_mask"
+  ],
+  "model_type": "qwen2_5_omni",
+  "pad_token_id": 151643,
+  "talker_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "Qwen2.5-Omni-3B/talker",
+    "architectures": [
+      "Qwen2OmniTalkerForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "dtype": "bfloat16",
+    "embedding_size": 2048,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "image_token_index": 151655,
+    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_omni_talker",
+    "num_attention_heads": 14,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "position_id_per_seconds": 25,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        16,
+        0
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "seconds_per_chunk": 2,
+    "sliding_window": null,
+    "spatial_merge_size": 2,
+    "tts_codec_end_token_id": 8294,
+    "tts_codec_mask_token_id": 8296,
+    "tts_codec_pad_token_id": 8292,
+    "tts_codec_start_token_id": 8293,
+    "tts_text_end_token_id": 151861,
+    "tts_text_pad_token_id": 151859,
+    "tts_text_start_token_id": 151860,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_index": 151656,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vocab_size": 8448
+  },
+  "thinker_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "Qwen2.5-Omni-3B/thinker",
+    "architectures": [
+      "Qwen2OmniNaViTThinkerForConditionalGeneration"
+    ],
+    "audio_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "activation_dropout": 0.0,
+      "activation_function": "gelu",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "d_model": 1280,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.0,
+      "dtype": "bfloat16",
+      "early_stopping": false,
+      "encoder_attention_heads": 20,
+      "encoder_ffn_dim": 5120,
+      "encoder_layerdrop": 0.0,
+      "encoder_layers": 32,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_source_positions": 1500,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_audio_encoder",
+      "n_window": 100,
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 32,
+      "num_mel_bins": 128,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_dim": 2048,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "scale_embedding": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "audio_end_token_id": 151648,
+    "audio_start_token_id": 151647,
+    "audio_token_index": 151646,
+    "bos_token_id": 151644,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "ignore_index": -100,
+    "image_token_index": 151655,
+    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "model_type": "qwen2_5_omni_thinker",
+    "pad_token_id": 151643,
+    "position_id_per_seconds": 25,
+    "seconds_per_chunk": 2,
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": "bfloat16",
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 11008,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 32768,
+      "max_window_layers": 70,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_text",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 36,
+      "num_key_value_heads": 2,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "mrope_section": [
+          16,
+          24,
+          24
+        ],
+        "rope_type": "default",
+        "type": "default"
+      },
+      "rope_theta": 1000000.0,
+      "sep_token_id": null,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 151936
+    },
+    "user_token_id": 872,
+    "video_token_index": 151656,
+    "vision_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 32,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": "bfloat16",
+      "early_stopping": false,
+      "embed_dim": 1280,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "fullatt_block_indexes": [
+        7,
+        15,
+        23,
+        31
+      ],
+      "hidden_act": "silu",
+      "hidden_size": 1280,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "in_chans": 3,
+      "init_std": 0.02,
+      "initializer_range": 0.02,
+      "intermediate_size": 3420,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_vision_encoder",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_heads": 16,
+      "num_return_sequences": 1,
+      "out_hidden_size": 2048,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 14,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "tokens_per_second": 25,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "window_size": 112
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654
+  },
+  "token2wav_config": {
+    "_attn_implementation_autoset": true,
+    "bigvgan_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": null,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "mel_dim": 80,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_bigvgan",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "upsample_initial_channel": 1536,
+      "upsample_kernel_sizes": [
+        11,
+        7,
+        4,
+        4,
+        4,
+        4
+      ],
+      "upsample_rates": [
+        5,
+        3,
+        2,
+        2,
+        2,
+        2
+      ],
+      "use_bfloat16": false,
+      "use_bias_at_final": false
+    },
+    "dit_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "block_size": 24,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 22,
+      "dim": 1024,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.1,
+      "dtype": "float32",
+      "early_stopping": false,
+      "emb_dim": 512,
+      "enc_attention_channels": 64,
+      "enc_channels": [
+        256,
+        256,
+        256,
+        256,
+        768
+      ],
+      "enc_dilations": [
+        1,
+        2,
+        3,
+        4,
+        1
+      ],
+      "enc_dim": 128,
+      "enc_emb_dim": 192,
+      "enc_global_context": true,
+      "enc_kernel_sizes": [
+        5,
+        3,
+        3,
+        3,
+        1
+      ],
+      "enc_lin_neurons": 192,
+      "enc_res2net_scale": 2,
+      "enc_se_channels": 64,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "ff_mult": 2,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 64,
+      "heads": 16,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "look_ahead_layers": [
+        10
+      ],
+      "look_backward_layers": [
+        0,
+        20
+      ],
+      "max_length": 20,
+      "max_position_embeddings": 32768,
+      "mel_dim": 80,
+      "min_length": 0,
+      "model_type": "qwen2_5_omni_dit",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_embeds": 8193,
+      "num_hidden_layers": 22,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repeats": 2,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rope_theta": 10000.0,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "dtype": "bfloat16",
+    "model_type": "qwen2_5_omni_token2wav",
+    "pad_token_id": 151643
+  },
+  "transformers_version": "4.56.0"
+}

Qwen2.5-Omni-3B-Chuan/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151643,
+    151645
+  ],
+  "transformers_version": "4.56.0"
+}

Qwen2.5-Omni-3B-Chuan/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5ce647e0d4852a38d4a76408898e54374f9397c2dcefa7314537a55c1e6b21
+size 1570766848

Qwen2.5-Omni-3B-Chuan/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694f5ce71776f6caf0a94ace088cd7eeafd3c1a30e029c6e1c7a70f8221df4ba
+size 1573912576

Qwen2.5-Omni-3B-Chuan/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedb25618881ce9466eefb9872e19e81f30d281dd2b139b8c8111ae7a9025e7b
+size 1582039040

Qwen2.5-Omni-3B-Chuan/preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "chunk_length": 300,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5OmniProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "temporal_patch_size": 2
+}

Qwen2.5-Omni-3B-Chuan/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_bos|>",
+    "<|vision_eos|>",
+    "<|vision_pad|>",
+    "<|IMAGE|>",
+    "<|VIDEO|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_token": "<|AUDIO|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<|IMAGE|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>"
+}

Qwen2.5-Omni-3B-Chuan/spk_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
+size 259544

Qwen2.5-Omni-3B-Chuan/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
+size 11421870

Qwen2.5-Omni-3B-Chuan/tokenizer_config.json

@@ -0,0 +1,222 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|AUDIO|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|audio_bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|audio_eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|IMAGE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|VIDEO|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_bos|>",
+    "<|vision_eos|>",
+    "<|vision_pad|>",
+    "<|IMAGE|>",
+    "<|VIDEO|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_token": "<|AUDIO|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_bos|>",
+    "audio_eos_token": "<|audio_eos|>",
+    "audio_token": "<|AUDIO|>",
+    "image_token": "<|IMAGE|>",
+    "video_token": "<|VIDEO|>",
+    "vision_bos_token": "<|vision_bos|>",
+    "vision_eos_token": "<|vision_eos|>"
+  },
+  "image_token": "<|IMAGE|>",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5OmniProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|VIDEO|>",
+  "vision_bos_token": "<|vision_bos|>",
+  "vision_eos_token": "<|vision_eos|>"
+}

Qwen2.5-Omni-3B-Chuan/video_preprocessor_config.json

@@ -0,0 +1,56 @@
+{
+  "chunk_length": 300,
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "fps": null,
+  "hop_length": 160,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "num_frames": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5OmniProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_metadata": false,
+  "sampling_rate": 16000,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

README.md

@@ -0,0 +1,91 @@
+---
+language: zh
+license: apache-2.0
+tags:
+  - automatic-speech-recognition
+  - ASR
+  - chinese
+  - speech
+---
+
+## 📂 Project Tree
+
+```
+WSChuan-ASR
+├── paraformer_large_chuan/
+│ ├── config.yaml
+│ ├── model.pt
+│ └── infer.py
+│
+├── Qwen2.5-omni3B/
+| ├──added_tokens.json
+| ├──args.json
+| ├──char_template.jinja
+| ├──config.json
+| ├──generation_config.json
+| ├──merges.txt
+| ├──model-00001-of-00003.safetensors
+| ├──model-00002-of-00003.safetensors
+| ├──model-00003-of-00003.safetensors
+| ├──model.safetensors.index.json
+| ├──preprocessor_config.json
+| ├──special_tokens_map.json
+| ├──spk_dict.pt
+| ├──tokenizer_config.json
+| ├──tokenizer.json
+| ├──video_preprocessor_config.json
+| └──vocab.json
+│
+├── .gitattributes
+└── README.md
+```
+
+## ASR Leaderboard
+| Model | Model Size | WSC-Eval-ASR - Easy | WSC-Eval-ASR - Hard | WSC-Eval-ASR - Total | Magicdata - Conversation | Magicdata - Daily-Use | Avg. |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| **with LLM** |  |  |  |  |  |  |  |
+| Kimi-Audio<sup></sup> | 7B | 16.65 | 28.66 | 17.66 | 24.67 | **5.77** | 18.68 |
+| FireRedASR-LLM<sup></sup> | 8.3B | 12.80 | 25.27 | 14.40 | 17.68 | 6.69 | 15.37 |
+| Qwen2.5-omni<sup></sup> | 3B | 16.94 | 26.01 | 18.20 | 20.40 | 6.32 | 17.69 |
+| Qwen2.5-omni-WSC-Finetune⭐ | 3B | 14.36 | 24.14 | 15.61 | 18.45 | 6.15 | 15.74 |
+| <span style="background-color: #d4edda; padding: 0 2px;">Qwen2.5-omni+internal data⭐</span> | 3B | 13.17 | 23.36 | 14.81 | 18.50 | 5.88 | 15.14 |
+| <span style="background-color: #d4edda; padding: 0 2px;">Qwen2.5-omni-WSC-Finetune + internal data⭐</span> | 3B | 12.93 | 23.19 | 14.25 | 17.95 | <u>5.89</u> | 14.84 |
+| **without LLM** |  |  |  |  |  |  |  |
+| SenseVoice-small<sup></sup> | 234M | 17.43 | 28.38 | 18.39 | 23.50 | 8.77 | 19.29 |
+| Whisper<sup></sup> | 244M | 52.06 | 63.99 | 53.59 | 55.88 | 52.03 | 55.51 |
+| FireRedASR-AED<sup></sup> | 1.1B | 13.29 | 23.64 | 14.62 | 17.84 | 6.69 | 15.14 |
+| Paraformer<sup></sup> | 220M | 14.34 | 24.61 | 15.66 | 19.81 | 8.16 | 16.52 |
+| Paraformer-WSC-Finetune⭐ | 220M | 12.15 | 22.60 | 13.51 | 16.60 | 8.02 | 14.58 |
+| <span style="background-color: #d4edda; padding: 0 2px;">Paraformer + internal data⭐</span> | 220M | <u>11.93</u> | <u>21.82</u> | <u>13.14</u> | <u>15.61</u> | 6.77 | <u>13.85</u> |
+| <span style="background-color: #d4edda; padding: 0 2px;">Paraformer-WSC-Finetune + internal data</span>⭐ | 220M | **11.59** | **21.59** | **12.87** | **14.59** | 6.28 | **13.38** |
+
+
+
+## ASR Inference
+### Paraformer_large_Chuan
+```
+export CUDA_VISIBLE_DEVICES=7
+root_dir=./test_data
+test_sets=("WSC-Eval-ASR" "WSC-Eval-ASR-Hard" "WSC-Eval-ASR-Easy")
+model_dir=./model_dir
+
+out_rootdir=./results
+mkdir -p $out_rootdir
+python infer_paraformer.py \
+  --model $model_dir \
+  --wav_scp_file $root_dir/$test_data/wav.scp \
+  --output_dir $out_rootdir/debug \
+  --device "cuda" \
+  --output_file $out_dir/hyp.txt
+```
+---
+
+### Qwen2.5-Omni-3B_Chuan
+```
+python infer_qwen2.5omni.py \
+    --wavs_path /path/to/your/wav.scp \
+    --out_path /path/to/your/results.txt \
+    --gpu 0 \
+    --model /path/to/your/model
+```
+

infer_paraformer.py

@@ -0,0 +1,65 @@
+import argparse
+import json
+import os
+from funasr import AutoModel
+
+
+def read_wav_scp(wav_scp_file: str):
+    """读取 wav.scp 文件，返回 (id, wav_path) 元组列表。"""
+    wav_files = []
+    with open(wav_scp_file, 'r') as f:
+        for line in f:
+            id, wav_path = line.strip().split(" ", 1)  # 只根据第一个空格切分
+            wav_files.append((id, wav_path))
+    return wav_files
+
+
+def save_results(results, output_file: str):
+    """将推理结果保存到指定的文件中，格式为 'key text' 每行一条。"""
+    with open(output_file, 'w') as f:
+        for result in results:
+            key = result.get("key", "")
+            text = result.get("text", "")
+            f.write(f"{key} {text}\n")
+
+
+def main():
+    # 解析命令行参数
+    parser = argparse.ArgumentParser(description="Run speech recognition inference")
+    parser.add_argument('--model', type=str, required=True, help="Model name or path")
+    parser.add_argument('--wav_scp_file', type=str, required=True, help="Path to wav.scp file")
+    parser.add_argument('--output_dir', type=str, required=True, help="Directory to save inference results")
+    parser.add_argument('--device', type=str, default="cpu", choices=["cpu", "cuda"], help="Device to run inference on")
+    parser.add_argument('--output_file', type=str, required=True, help="File to save the inference results")
+
+    args = parser.parse_args()
+
+    # 初始化模型
+    print(f"Initializing model {args.model}...")
+    model = AutoModel(model=args.model, device=args.device)
+
+    # 读取 wav.scp 文件
+    wav_files = read_wav_scp(args.wav_scp_file)
+
+    # 存储所有推理结果
+    all_results = []
+
+    # 遍历每个音频文件并进行推理
+    for id, wav_path in wav_files:
+        print(f"正在处理音频文件 {id}: {wav_path}")
+        res = model.generate(wav_path)
+        print(f"推理结果: {res}")
+
+        if res:
+            # 提取推理结果中的 key 和 text
+            key = id
+            text = res[0].get("text", "")
+            all_results.append({"key": key, "text": text})
+
+    # 将推理结果保存到文件
+    save_results(all_results, args.output_file)
+    print(f"推理结果已保存到 {args.output_file}")
+
+
+if __name__ == "__main__":
+    main()

infer_qwen2.5omni.py

@@ -0,0 +1,68 @@
+from qwen_omni_utils import process_mm_info
+import torch
+from transformers import Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniProcessor
+import librosa
+import os 
+from io import BytesIO
+from urllib.request import urlopen
+import argparse
+# @title inference function
+def inference(audio_path,model,processor,prompt, sys_prompt):
+    messages = [
+        {"role": "system", "content": [{"type": "text", "text": sys_prompt}]},
+        {"role": "user", "content": [
+                {"type": "audio", "audio": audio_path},
+                {"type": "text", "text": prompt},
+            ]
+        },
+    ]
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    audios, images, videos = process_mm_info(messages, use_audio_in_video=True)
+    inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=True)
+    inputs = inputs.to(model.device).to(model.dtype)
+
+    output = model.generate(**inputs, use_audio_in_video=True, return_audio=False, thinker_max_new_tokens=256, thinker_do_sample=False)
+
+    text = processor.batch_decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+    return text
+
+def transcribe(wavs_path, out_path, gpu_id, model):
+    os.environ["CUDA_VISIBLE_DEVICES"] = str(gpu_id)
+    model_path = model
+    model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
+                model_path,
+                torch_dtype=torch.bfloat16,
+                device_map="auto",
+        )
+    prompt = "请将这段中文语音转换为纯文本，去掉标点符号。"
+    processor = Qwen2_5OmniProcessor.from_pretrained(model_path)
+    with open(wavs_path, "r") as f_in, open(out_path, "w") as f_out:
+        for line in f_in:
+            utt, path = line.strip().split(" ", maxsplit=1)
+            try:
+                response=inference(path,model,processor, prompt=prompt, sys_prompt="You are a speech recognition model.")
+            except Exception as e:
+                print(f"Inference failed: {str(e)}")  
+                response="None"
+            text = response[0].strip()
+            lines = text.strip().splitlines()
+            text = lines[-1]
+            print(f"[{utt}] >>> {text}")
+            f_out.write(f"{utt} {text}\n")
+
+
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--wavs_path", type=str)
+    parser.add_argument("--out_path", type=str)
+    parser.add_argument("--gpu", type=int, default=0)
+    parser.add_argument("--model", type=str)
+    args = parser.parse_args()
+    transcribe(
+        wavs_path=args.wavs_path,
+        out_path=args.out_path,
+        gpu_id=args.gpu,
+        model=args.model
+    )