(k2-python) luomingshuang@de-74279-k2-train-3-0602204318-5799c545db-hhjfr:~/codes/icefall-pruned-rnnt5-aishell4/egs/aishell4/ASR$ CUDA_VISIBLE_DEVICES='0' python pruned_transducer_stateless5/pretrained.py --checkpoint icefall_asr_aishell4_pruned_transducer_stateless5/exp/pretrained_iter_36000_avg_8.pt --lang-dir icefall_asr_aishell4_pruned_transducer_stateless5/data/lang_char --decoding-method greedy_search icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment1.flac icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment2.flac icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment3.flac
2022-06-13 21:50:50,596 INFO [lexicon.py:176] Loading pre-compiled icefall_asr_aishell4_pruned_transducer_stateless5/data/lang_char/Linv.pt
2022-06-13 21:50:50,605 INFO [pretrained.py:225] {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 100, 'valid_interval': 200, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 400, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.3.0.dev+git.e740036.dirty', 'torch-version': '1.11.0', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'icefall-pruned-rnnt5-aishell4', 'icefall-git-sha1': 'c8cb425-dirty', 'icefall-git-date': 'Wed Jun 8 15:35:53 2022', 'icefall-path': '/ceph-meixu/luomingshuang/icefall', 'k2-path': '/ceph-ms/luomingshuang/k2_latest/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-meixu/luomingshuang/anaconda3/envs/k2-python/lib/python3.8/site-packages/lhotse-1.3.0.dev0+git.e740036.dirty-py3.8.egg/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-0602204318-5799c545db-hhjfr', 'IP address': '10.177.24.137'}, 'checkpoint': 'icefall_asr_aishell4_pruned_transducer_stateless5/exp/pretrained_iter_36000_avg_8.pt', 'lang_dir': 'icefall_asr_aishell4_pruned_transducer_stateless5/data/lang_char', 'decoding_method': 'greedy_search', 'sound_files': ['icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment1.flac', 'icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment2.flac', 'icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment3.flac'], 'sample_rate': 16000, 'beam_size': 4, 'beam': 4, 'max_contexts': 4, 'max_states': 8, 'context_size': 2, 'max_sym_per_frame': 1, 'num_encoder_layers': 24, 'dim_feedforward': 1536, 'nhead': 8, 'encoder_dim': 384, 'decoder_dim': 512, 'joiner_dim': 512, 'blank_id': 0, 'vocab_size': 3284}
2022-06-13 21:50:50,605 INFO [pretrained.py:231] device: cuda:0
2022-06-13 21:50:50,605 INFO [pretrained.py:233] Creating model
2022-06-13 21:50:51,112 INFO [pretrained.py:237] Number of model parameters: 94337552
2022-06-13 21:50:54,940 INFO [pretrained.py:245] Constructing Fbank computer
2022-06-13 21:50:54,941 INFO [pretrained.py:255] Reading sound files: ['icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment1.flac', 'icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment2.flac', 'icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment3.flac']
2022-06-13 21:50:54,998 INFO [pretrained.py:261] Decoding started
2022-06-13 21:50:55,636 INFO [pretrained.py:280] Using greedy_search
2022-06-13 21:50:55,680 INFO [pretrained.py:338]
icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment1.flac:
嗯 这 次 呢 咱 们 就 把 各 家 长 叫 过 来 咱 简 单 开 的 家 长 的 一 个 交 流 会

icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment2.flac:
呃 玩 具 呀 说 一 下 各 个 孩 子 的 大 家 的 一 些 情 况 包 括 那 些 情 况

icefall_asr_aishell4_pruned_transducer_stateless5/test_wavs/test_segment3.flac:
因 为 提 供 考 试 啊 嗯 刚 过 嘛 嗯 呃 我 这 边 儿


2022-06-13 21:50:55,681 INFO [pretrained.py:340] Decoding Done