Created by: YuHuasong123

aishell$ sh run_data.sh Skip downloading and unpacking. Data already exists in ./dataset/aishell. Creating manifest data/aishell/manifest ... ----------- Configuration Arguments ----------- count_threshold: 0 manifest_paths: ['data/aishell/manifest.train', 'data/aishell/manifest.dev'] vocab_path: data/aishell/vocab.txt

----------- Configuration Arguments ----------- manifest_path: data/aishell/manifest.train num_samples: 2000 output_path: data/aishell/mean_std.npz specgram_type: linear

0 2000 Traceback (most recent call last): File "tools/compute_mean_std.py", line 51, in main() File "tools/compute_mean_std.py", line 46, in main num_samples=args.num_samples) File "/home/aistudio/DeepSpeech/tools/../data_utils/normalizer.py", line 46, in init self._compute_mean_std(manifest_path, featurize_func, num_samples) File "/home/aistudio/DeepSpeech/tools/../data_utils/normalizer.py", line 80, in _compute_mean_std sampled_manifest = self._rng.sample(manifest, num_samples) File "/opt/conda/envs/python27-paddle120-env/lib/python2.7/random.py", line 325, in sample raise ValueError("sample larger than population") ValueError: sample larger than population Compute mean and stddev failed. Terminated.