hparams)
plot_spec(
norm(spec_orig),
fig=None,
ax=None,
rate=None,
hop_len_ms=None,
cmap=plt.cm.afmhot,
show_cbar=True,
figsize=(20, 6),
)
# segment
results = dynamic_threshold_segmentation(data,
hparams,
verbose=True,
min_syllable_length_s=min_syllable_length_s,
spectral_range=spectral_range)
plot_segmentations(
results["spec"],
results["vocal_envelope"],
results["onsets"],
results["offsets"],
int(hparams.hop_length_ms),
int(hparams.sample_rate),
figsize=(15,5)
)
plt.show()
# Function for batch processing all segments
def segment_spec_custom(key, df, DT_ID, save=False, plot=False):
# load wav
rate, data = load_wav(df.data["wav_loc"])
# filter data
data = butter_bandpass_filter(data, butter_min, butter_max, rate)
# segment
# results = dynamic_threshold_segmentation(
# data,
# rate,
# n_fft=n_fft,
# hop_length_ms=hop_length_ms,
# win_length_ms=win_length_ms,
# min_level_db_floor=min_level_db_floor,
# db_delta=db_delta,
# ref_level_db=ref_level_db,
# pre=pre,
# min_silence_for_spec=min_silence_for_spec,
# max_vocal_for_spec=max_vocal_for_spec,
# min_level_db=min_level_db,
# silence_threshold=silence_threshold,
# verbose=True,
# min_syllable_length_s=min_syllable_length_s,
# spectral_range=spectral_range,
# )
results = dynamic_threshold_segmentation(data,
hparams,
verbose=True,
min_syllable_length_s=min_syllable_length_s,
spectral_range=spectral_range)
if results is None:
return
if plot:
plot_segmentations(
results["spec"],
results["vocal_envelope"],
results["onsets"],
results["offsets"],
hop_length_ms,
rate,
figsize=(15, 3)
)
plt.show()
# save the results
json_out = DATA_DIR / "processed" / (DATASET_ID + "_segmented") / DT_ID / "JSON" / (
key + ".JSON"
)
json_dict = df.data.copy()
json_dict["indvs"][list(df.data["indvs"].keys())[0]]["syllables"] = {
"start_times": list(results["onsets"]),
"end_times": list(results["offsets"]),
}
json_txt = json.dumps(json_dict, cls=NoIndentEncoder, indent=2)
# save json
if save:
ensure_dir(json_out.as_posix())
with open(json_out.as_posix(), "w") as json_file:
json.dump(json_dict, json_file, cls=NoIndentEncoder, indent=2)
json_file.close()
# print(json_txt, file=open(json_out.as_posix(), "w"))
#print(json_txt)
return results
data = data / np.max(np.abs(data))
# filter data
data = butter_bandpass_filter(data, butter_min, butter_max, rate)
plt.plot(data)
# segment
results = dynamic_threshold_segmentation(
data,
rate,
n_fft=n_fft,
hop_length_ms=hop_length_ms,
win_length_ms=win_length_ms,
min_level_db_floor=min_level_db_floor,
db_delta=db_delta,
ref_level_db=ref_level_db,
pre=pre,
min_silence_for_spec=min_silence_for_spec,
max_vocal_for_spec=max_vocal_for_spec,
min_level_db=min_level_db,
silence_threshold=silence_threshold,
verbose=True,
min_syllable_length_s=min_syllable_length_s,
spectral_range=spectral_range,
)
plot_segmentations(results["spec"],
results["vocal_envelope"],
results["onsets"],
results["offsets"],
int(hparams.hop_length_ms),
int(hparams.sample_rate),