From ab962d41126dadf38eb003951332d46403fac391 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=AC=AC=E7=B4=97=E7=89=B9?=
 <66856838+Miuzarte@users.noreply.github.com>
Date: Sun, 12 Mar 2023 00:07:29 +0800
Subject: [PATCH] Increase convenience for colab training

---
 configs/config.json                   | 65 ---------------------------
 configs_template/config_template.json | 65 +++++++++++++++++++++++++++
 preprocess_flist_config.py            |  2 +-
 3 files changed, 66 insertions(+), 66 deletions(-)
 create mode 100644 configs_template/config_template.json

diff --git a/configs/config.json b/configs/config.json
index f19d46d..e69de29 100644
--- a/configs/config.json
+++ b/configs/config.json
@@ -1,65 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 800,
-    "seed": 1234,
-    "epochs": 10000,
-    "learning_rate": 0.0001,
-    "betas": [
-      0.8,
-      0.99
-    ],
-    "eps": 1e-09,
-    "batch_size": 6,
-    "fp16_run": false,
-    "lr_decay": 0.999875,
-    "segment_size": 10240,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "use_sr": true,
-    "max_speclen": 512,
-    "port": "8001",
-    "keep_ckpts": 3
-  },
-  "data": {
-    "training_files": "filelists/train.txt",
-    "validation_files": "filelists/val.txt",
-    "max_wav_value": 32768.0,
-    "sampling_rate": 44100,
-    "filter_length": 2048,
-    "hop_length": 512,
-    "win_length": 2048,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": 22050
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0.1,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [ 8, 8, 2, 2, 2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16, 4, 4, 4],
-    "n_layers_q": 3,
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "ssl_dim": 256,
-    "n_speakers": 200
-  },
-  "spk": {
-    "nyaru": 0,
-    "huiyu": 1,
-    "nen": 2,
-    "paimon": 3,
-    "yunhao": 4
-  }
-}
\ No newline at end of file
diff --git a/configs_template/config_template.json b/configs_template/config_template.json
new file mode 100644
index 0000000..f19d46d
--- /dev/null
+++ b/configs_template/config_template.json
@@ -0,0 +1,65 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [ 8, 8, 2, 2, 2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16, 4, 4, 4],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "nyaru": 0,
+    "huiyu": 1,
+    "nen": 2,
+    "paimon": 3,
+    "yunhao": 4
+  }
+}
\ No newline at end of file
diff --git a/preprocess_flist_config.py b/preprocess_flist_config.py
index ff5c969..9a7da50 100644
--- a/preprocess_flist_config.py
+++ b/preprocess_flist_config.py
@@ -7,7 +7,7 @@ from random import shuffle
 import json
 import wave
 
-config_template = json.load(open("configs/config.json"))
+config_template = json.load(open("configs_template/config_template.json"))
 
 pattern = re.compile(r'^[\.a-zA-Z0-9_\/]+$')