def main(argv):
speech_file = argv[1]
feature_type = argv[2]
augments = {
# "after": {
# "time_masking": {
# "num_masks": 10,
# "mask_factor": 100,
# "p_upperbound": 0.05
# },
# "freq_masking": {
# "mask_factor": 27
# }
# },
}
au = UserAugmentation(augments)
speech_conf = {
"sample_rate": 16000,
"frame_ms": 25,
"stride_ms": 10,
"feature_type": feature_type,
"preemphasis": 0.97,
"normalize_signal": True,
"normalize_feature": True,
"normalize_per_feature": False,
"num_feature_bins": 80,
}
signal = read_raw_audio(speech_file, speech_conf["sample_rate"])
sf = NumpySpeechFeaturizer(speech_conf)
ft = sf.extract(signal)
ft = au["after"].augment(ft)[:, :, 0]
plt.figure(figsize=(16, 2.5))
ax = plt.gca()
ax.set_title(f"{feature_type}", fontweight="bold")
librosa.display.specshow(ft.T, cmap="magma")
v1 = np.linspace(ft.min(), ft.max(), 8, endpoint=True)
plt.colorbar(pad=0.01, fraction=0.02, ax=ax, format="%.2f", ticks=v1)
plt.tight_layout()
plt.savefig(argv[3])
plt.show()
from tiramisu_asr.featurizers.speech_featurizers import TFSpeechFeaturizer
from tiramisu_asr.featurizers.speech_featurizers import NumpySpeechFeaturizer
from tiramisu_asr.featurizers.text_featurizers import SubwordFeaturizer
from tiramisu_asr.optimizers.schedules import TransformerSchedule
from multiconformers_trainer import MultiConformersTrainer
from multiconformers_dataset import MultiConformersTFRecordDataset, MultiConformersSliceDataset
config = UserConfig(DEFAULT_YAML, args.config, learning=True)
lms_config = config["speech_config"]
lms_config["feature_type"] = "log_mel_spectrogram"
lgs_config = config["speech_config"]
lgs_config["feature_type"] = "log_gammatone_spectrogram"
if args.nfx:
speech_featurizer_lms = NumpySpeechFeaturizer(lms_config)
speech_featurizer_lgs = NumpySpeechFeaturizer(lgs_config)
else:
speech_featurizer_lms = TFSpeechFeaturizer(lms_config)
speech_featurizer_lgs = TFSpeechFeaturizer(lgs_config)
if args.subwords_prefix and os.path.exists(f"{args.subwords_prefix}.subwords"):
print("Loading subwords ...")
text_featurizer = SubwordFeaturizer.load_from_file(
config["decoder_config"], args.subwords_prefix)
else:
print("Generating subwords ...")
text_featurizer = SubwordFeaturizer.build_from_corpus(
config["decoder_config"], corpus_files=args.subwords_corpus)
text_featurizer.subwords.save_to_file(args.subwords_prefix)