From d8f98c07b4f56055b785b75a50dcc58603dbe7a5 Mon Sep 17 00:00:00 2001
From: Johan Nordberg <its@johan-nordberg.com>
Date: Sun, 29 May 2022 01:10:19 +0000
Subject: [PATCH] Remove some assumptions about working directory This allows
cli tool to run when not standing in repository dir
---
tortoise/models/arch_util.py | 6 +++++-
tortoise/utils/audio.py | 5 ++++-
tortoise/utils/tokenizer.py | 6 +++++-
3 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/tortoise/models/arch_util.py b/tortoise/models/arch_util.py
index 5d8c36e..6a79194 100644
--- a/tortoise/models/arch_util.py
+++ b/tortoise/models/arch_util.py
@@ -1,3 +1,4 @@
+import os
import functools
import math
@@ -288,9 +289,12 @@ class AudioMiniEncoder(nn.Module):
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):
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__()
# These are the default tacotron values for the MEL spectrogram.
self.filter_length = filter_length
diff --git a/tortoise/utils/audio.py b/tortoise/utils/audio.py
index 7d5390c..b125258 100644
--- a/tortoise/utils/audio.py
+++ b/tortoise/utils/audio.py
@@ -10,6 +10,9 @@ from scipy.io.wavfile import read
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):
sampling_rate, data = read(full_path)
if data.dtype == np.int32:
@@ -83,7 +86,7 @@ def dynamic_range_decompression(x, C=1):
def get_voices(extra_voice_dirs=[]):
- dirs = ['tortoise/voices'] + extra_voice_dirs
+ dirs = [BUILTIN_VOICES_DIR] + extra_voice_dirs
voices = {}
for d in dirs:
subs = os.listdir(d)
diff --git a/tortoise/utils/tokenizer.py b/tortoise/utils/tokenizer.py
index a8959d8..3ab1c31 100644
--- a/tortoise/utils/tokenizer.py
+++ b/tortoise/utils/tokenizer.py
@@ -1,3 +1,4 @@
+import os
import re
import inflect
@@ -165,8 +166,11 @@ def lev_distance(s1, s2):
return distances[-1]
+DEFAULT_VOCAB_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../data/tokenizer.json')
+
+
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:
self.tokenizer = Tokenizer.from_file(vocab_file)