Use clap to achieve prompt controlled generation (#223)

* 快速分类音频并把yml格式结果存在训练根目录里 (#190)

* Add files via upload

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Update models.py

* Update webui.py

* Update infer.py

* Create compress_model.py

* 重新提交，更新Gradio推理UI (#193)

* Update webui.py

* Update webui.py

* 更新 train_ms.py

* 更新 models.py

* 更新 models.py

* 更新 models.py

* 更新 train_ms.py

* 更新 train_ms.py

* 更新 models.py

* Update preprocess_text.py

* Update config.json

* Update train_ms.py

* Update webui.py (#206)

* Add files via upload (#209)

* Update train_ms.py

* Update train_ms.py

* Update preprocess_text.py

* Update train_ms.py

* fix (#211)

* Update emotion_clustering.py

* Add files via upload

* Update emotion_clustering.py

* add cluster center save

* Add files via upload

* Update config.py

* Update default_config.yml

* Update config.py

* Update config.py

* Update emotion_clustering.py

* Update emotion_clustering.py

* Update config.py

* Update emotion_clustering.py

* Update emotion_clustering.py

* Update webui.py

* Update emotion_clustering.py

* Update commons.py

* Update emotion_clustering.py

* Update webui.py

* Update webui.py

* Add files via upload

* Update train_ms.py

* Update train_ms.py

* Update train_ms.py

* Update train_ms.py

* Update train_ms.py

* Update webui.py

* Update emotion_clustering.py

* Update emotion_clustering.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix default_config.yml.

* Update infer.py

* feat: support infer 2.1 models

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix: support infer 2.1 models 兼容bug修复

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update train_ms.py

* Add CLAP

* Fix data loader

* Fix infer.py

* Fix webui.py

* Add prompt template

* Update clap_gen.py

* Fix wrong environ value

* Add g for dur disc

* Update clap_gen.py

* Fix multilang generation

* Update config.json

* Prompt mode

* Improve slice segments performance

* Add preprocess webui

* Update webui_preprocess.py

* Update webui_preprocess.py

* Update config.py

* Update default_config.yml

* Update config.py

* Update clap_gen.py

* Delete emo_gen.py

* Delete get_emo.py

* Delete emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim directory

* Update README.md

* Update README

* Split val per lang

* Delete emotion_clustering.py

* Update default_config.yml

* Update default_config.yml

* Update config.py

* Update preprocess_text.py

* Update webui_preprocess.py

* Update defalut_config.yml

* Update webui_preprocess.py

* Update preprocess_text.py

* Random augmentation for CLAP

* Update data_utils.py

* Update preprocess_text.py

* Add vq for CLAP features to avoid overfitting

* Random dummy inputs

* Update webui.py

* Update models.py

* Update infer.py

* Apply Code Formatter Change

* Update config.json

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: YYuX-1145 <138500330+YYuX-1145@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Sora <654163754@qq.com>
Co-authored-by: Sihan Wang <wangsihan1995@gmail.com>
Co-authored-by: Stardust-minus <Stardust-minus@users.noreply.github.com>

clap_gen.py

@@ -0,0 +1,64 @@
+import argparse
+from multiprocessing import Pool, cpu_count
+
+import torch
+import torch.multiprocessing as mp
+from tqdm import tqdm
+
+import utils
+from config import config
+from clap_wrapper import get_clap_audio_feature
+import librosa
+import os
+
+os.environ["OMP_NUM_THREADS"] = "1"
+os.environ["MKL_NUM_THREADS"] = "1"
+
+
+def process_line(line):
+    device = config.emo_gen_config.device
+    if config.emo_gen_config.use_multi_device:
+        rank = mp.current_process()._identity
+        rank = rank[0] if len(rank) > 0 else 0
+        if torch.cuda.is_available():
+            gpu_id = rank % torch.cuda.device_count()
+            device = torch.device(f"cuda:{gpu_id}")
+        else:
+            device = torch.device("cpu")
+    wav_path, _, language_str, text, phones, tone, word2ph = line.strip().split("|")
+
+    clap_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".emo.npy")
+    if os.path.isfile(clap_path):
+        return
+
+    audio = librosa.load(wav_path, 48000)[0]
+    # audio = librosa.resample(audio, 44100, 48000)
+
+    clap = get_clap_audio_feature(audio, device)
+    torch.save(clap, clap_path)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-c", "--config", type=str, default=config.emo_gen_config.config_path
+    )
+    parser.add_argument(
+        "--num_processes", type=int, default=config.emo_gen_config.num_processes
+    )
+    args, _ = parser.parse_known_args()
+    config_path = args.config
+    hps = utils.get_hparams_from_file(config_path)
+    lines = []
+    with open(hps.data.training_files, encoding="utf-8") as f:
+        lines.extend(f.readlines())
+
+    with open(hps.data.validation_files, encoding="utf-8") as f:
+        lines.extend(f.readlines())
+    if len(lines) != 0:
+        num_processes = min(args.num_processes, cpu_count())
+        with Pool(processes=num_processes) as pool:
+            for _ in tqdm(pool.imap_unordered(process_line, lines), total=len(lines)):
+                pass
+
+    print(f"clap生成完毕!, 共有{len(lines)}个emo.pt生成!")