| | |
| | | parser = get_parser() |
| | | args = parser.parse_args() |
| | | |
| | | wav_scp_file = os.path.join(args.wav_path + "{}/wav.scp".format(args.idx)) |
| | | cmvn_file = os.path.join(args.wav_path + "{}/cmvn.json".format(args.idx)) |
| | | wav_scp_file = os.path.join(args.wav_path, "wav.{}.scp".format(args.idx)) |
| | | cmvn_file = os.path.join(args.wav_path, "cmvn.{}.json".format(args.idx)) |
| | | |
| | | mean_stats = np.zeros(args.dims) |
| | | var_stats = np.zeros(args.dims) |
| | | mean_stats = np.zeros(args.dim) |
| | | var_stats = np.zeros(args.dim) |
| | | total_frames = 0 |
| | | |
| | | # with ReadHelper('ark:{}'.format(ark_file)) as ark_reader: |
| | |
| | | lines = f.readlines() |
| | | for line in lines: |
| | | _, wav_file = line.strip().split() |
| | | fbank = compute_fbank(wav_file, num_mel_bins=args.dims) |
| | | fbank = compute_fbank(wav_file, num_mel_bins=args.dim) |
| | | mean_stats += np.sum(fbank, axis=0) |
| | | var_stats += np.sum(np.square(fbank), axis=0) |
| | | total_frames += fbank.shape[0] |