wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-11 12:00:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

reformatting and styling

Browse Source
This commit is contained in:
Eren Gölge
2021-04-12 11:47:39 +02:00
parent 9011dddf77
commit f519012dea
159 changed files with 6589 additions and 6429 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/dataset_analysis/analyze.py
+41 -46
View File
@@ -1,16 +1,17 @@
# visualisation tools for mimic2
import matplotlib.pyplot as plt
from statistics import stdev, mode, mean, median
from statistics import StatisticsError
import argparse
import os
import csv
import seaborn as sns
import os
import random
from statistics import StatisticsError, mean, median, mode, stdev
import matplotlib.pyplot as plt
import seaborn as sns
from text.cmudict import CMUDict
def get_audio_seconds(frames):
return (frames*12.5)/1000
return (frames * 12.5) / 1000
def append_data_statistics(meta_data):
@@ -27,9 +28,7 @@ def append_data_statistics(meta_data):
median_audio_len = median(audio_len_list)
try:
std = stdev(
d["audio_len"] for d in data
)
std = stdev(d["audio_len"] for d in data)
except StatisticsError:
std = 0
@@ -44,24 +43,22 @@ def process_meta_data(path):
meta_data = {}
# load meta data
with open(path, 'r') as f:
data = csv.reader(f, delimiter='|')
with open(path, "r") as f:
data = csv.reader(f, delimiter="|")
for row in data:
frames = int(row[2])
utt = row[3]
audio_len = get_audio_seconds(frames)
char_count = len(utt)
if not meta_data.get(char_count):
meta_data[char_count] = {
"data": []
}
meta_data[char_count] = {"data": []}
meta_data[char_count]["data"].append(
{
"utt": utt,
"frames": frames,
"audio_len": audio_len,
"row": "{}|{}|{}|{}".format(row[0], row[1], row[2], row[3])
"row": "{}|{}|{}|{}".format(row[0], row[1], row[2], row[3]),
}
)
@@ -72,30 +69,30 @@ def process_meta_data(path):
def get_data_points(meta_data):
x = meta_data
y_avg = [meta_data[d]['mean'] for d in meta_data]
y_mode = [meta_data[d]['mode'] for d in meta_data]
y_median = [meta_data[d]['median'] for d in meta_data]
y_std = [meta_data[d]['std'] for d in meta_data]
y_num_samples = [len(meta_data[d]['data']) for d in meta_data]
y_avg = [meta_data[d]["mean"] for d in meta_data]
y_mode = [meta_data[d]["mode"] for d in meta_data]
y_median = [meta_data[d]["median"] for d in meta_data]
y_std = [meta_data[d]["std"] for d in meta_data]
y_num_samples = [len(meta_data[d]["data"]) for d in meta_data]
return {
"x": x,
"y_avg": y_avg,
"y_mode": y_mode,
"y_median": y_median,
"y_std": y_std,
"y_num_samples": y_num_samples
"y_num_samples": y_num_samples,
}
def save_training(file_path, meta_data):
rows = []
for char_cnt in meta_data:
data = meta_data[char_cnt]['data']
data = meta_data[char_cnt]["data"]
for d in data:
rows.append(d['row'] + "\n")
rows.append(d["row"] + "\n")
random.shuffle(rows)
with open(file_path, 'w+') as f:
with open(file_path, "w+") as f:
for row in rows:
f.write(row)
@@ -106,15 +103,15 @@ def plot(meta_data, save_path=None):
save = True
graph_data = get_data_points(meta_data)
x = graph_data['x']
y_avg = graph_data['y_avg']
y_std = graph_data['y_std']
y_mode = graph_data['y_mode']
y_median = graph_data['y_median']
y_num_samples = graph_data['y_num_samples']
x = graph_data["x"]
y_avg = graph_data["y_avg"]
y_std = graph_data["y_std"]
y_mode = graph_data["y_mode"]
y_median = graph_data["y_median"]
y_num_samples = graph_data["y_num_samples"]
plt.figure()
plt.plot(x, y_avg, 'ro')
plt.plot(x, y_avg, "ro")
plt.xlabel("character lengths", fontsize=30)
plt.ylabel("avg seconds", fontsize=30)
if save:
@@ -122,7 +119,7 @@ def plot(meta_data, save_path=None):
plt.savefig(os.path.join(save_path, name))
plt.figure()
plt.plot(x, y_mode, 'ro')
plt.plot(x, y_mode, "ro")
plt.xlabel("character lengths", fontsize=30)
plt.ylabel("mode seconds", fontsize=30)
if save:
@@ -130,7 +127,7 @@ def plot(meta_data, save_path=None):
plt.savefig(os.path.join(save_path, name))
plt.figure()
plt.plot(x, y_median, 'ro')
plt.plot(x, y_median, "ro")
plt.xlabel("character lengths", fontsize=30)
plt.ylabel("median seconds", fontsize=30)
if save:
@@ -138,7 +135,7 @@ def plot(meta_data, save_path=None):
plt.savefig(os.path.join(save_path, name))
plt.figure()
plt.plot(x, y_std, 'ro')
plt.plot(x, y_std, "ro")
plt.xlabel("character lengths", fontsize=30)
plt.ylabel("standard deviation", fontsize=30)
if save:
@@ -146,7 +143,7 @@ def plot(meta_data, save_path=None):
plt.savefig(os.path.join(save_path, name))
plt.figure()
plt.plot(x, y_num_samples, 'ro')
plt.plot(x, y_num_samples, "ro")
plt.xlabel("character lengths", fontsize=30)
plt.ylabel("number of samples", fontsize=30)
if save:
@@ -159,8 +156,8 @@ def plot_phonemes(train_path, cmu_dict_path, save_path):
phonemes = {}
with open(train_path, 'r') as f:
data = csv.reader(f, delimiter='|')
with open(train_path, "r") as f:
data = csv.reader(f, delimiter="|")
phonemes["None"] = 0
for row in data:
words = row[3].split()
@@ -192,15 +189,12 @@ def plot_phonemes(train_path, cmu_dict_path, save_path):
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--train_file_path', required=True,
help='this is the path to the train.txt file that the preprocess.py script creates'
)
parser.add_argument(
'--save_to', help='path to save charts of data to'
)
parser.add_argument(
'--cmu_dict_path', help='give cmudict-0.7b to see phoneme distribution'
"--train_file_path",
required=True,
help="this is the path to the train.txt file that the preprocess.py script creates",
)
parser.add_argument("--save_to", help="path to save charts of data to")
parser.add_argument("--cmu_dict_path", help="give cmudict-0.7b to see phoneme distribution")
args = parser.parse_args()
meta_data = process_meta_data(args.train_file_path)
plt.rcParams["figure.figsize"] = (10, 5)
@@ -211,5 +205,6 @@ def main():
plt.show()
if __name__ == '__main__':
if __name__ == "__main__":
main()