KwamaEggStew/tortoise-tts
1
0
Fork 0
forked from mrq/tortoise-tts
Code Pull Requests Activity

Remove some assumptions about working directory

Browse Source 
This allows cli tool to run when not standing in repository dir
This commit is contained in:
Johan Nordberg 2022-05-29 01:10:19 +00:00
parent a641d8f29b
commit 491fe7f6d3
3 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tortoise/models/arch_util.py
View File

@ -1,3 +1,4 @@
import os
import functools import functools
import math import math
@ -288,9 +289,12 @@ class AudioMiniEncoder(nn.Module):
return h[:, :, 0] return h[:, :, 0]
DEFAULT_MEL_NORM_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../data/mel_norms.pth')
class TorchMelSpectrogram(nn.Module): class TorchMelSpectrogram(nn.Module):
def __init__(self, filter_length=1024, hop_length=256, win_length=1024, n_mel_channels=80, mel_fmin=0, mel_fmax=8000, def __init__(self, filter_length=1024, hop_length=256, win_length=1024, n_mel_channels=80, mel_fmin=0, mel_fmax=8000,
sampling_rate=22050, normalize=False, mel_norm_file='tortoise/data/mel_norms.pth'): sampling_rate=22050, normalize=False, mel_norm_file=DEFAULT_MEL_NORM_FILE):
super().__init__() super().__init__()
# These are the default tacotron values for the MEL spectrogram. # These are the default tacotron values for the MEL spectrogram.
self.filter_length = filter_length self.filter_length = filter_length

5
tortoise/utils/audio.py
View File

@ -10,6 +10,9 @@ from scipy.io.wavfile import read
from tortoise.utils.stft import STFT from tortoise.utils.stft import STFT
BUILTIN_VOICES_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../voices')
def load_wav_to_torch(full_path): def load_wav_to_torch(full_path):
sampling_rate, data = read(full_path) sampling_rate, data = read(full_path)
if data.dtype == np.int32: if data.dtype == np.int32:
@ -83,7 +86,7 @@ def dynamic_range_decompression(x, C=1):
def get_voices(extra_voice_dirs=[]): def get_voices(extra_voice_dirs=[]):
dirs = ['tortoise/voices'] + extra_voice_dirs dirs = [BUILTIN_VOICES_DIR] + extra_voice_dirs
voices = {} voices = {}
for d in dirs: for d in dirs:
subs = os.listdir(d) subs = os.listdir(d)

6
tortoise/utils/tokenizer.py
View File

@ -1,3 +1,4 @@
import os
import re import re
import inflect import inflect
@ -165,8 +166,11 @@ def lev_distance(s1, s2):
return distances[-1] return distances[-1]
DEFAULT_VOCAB_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../data/tokenizer.json')
class VoiceBpeTokenizer: class VoiceBpeTokenizer:
def __init__(self, vocab_file='tortoise/data/tokenizer.json'): def __init__(self, vocab_file=DEFAULT_VOCAB_FILE):
if vocab_file is not None: if vocab_file is not None:
self.tokenizer = Tokenizer.from_file(vocab_file) self.tokenizer = Tokenizer.from_file(vocab_file)