Add better voice clones and prepare for finetuning

hubert/hubert_manager.py

@@ -0,0 +1,35 @@
+# From https://github.com/gitmylo/bark-voice-cloning-HuBERT-quantizer
+
+import os.path
+import shutil
+import urllib.request
+
+import huggingface_hub
+
+
+class HuBERTManager:
+    @staticmethod
+    def make_sure_hubert_installed(download_url: str = 'https://dl.fbaipublicfiles.com/hubert/hubert_base_ls960.pt', file_name: str = 'hubert.pt'):
+        install_dir = os.path.join('data', 'models', 'hubert')
+        if not os.path.isdir(install_dir):
+            os.makedirs(install_dir, exist_ok=True)
+        install_file = os.path.join(install_dir, file_name)
+        if not os.path.isfile(install_file):
+            print('Downloading HuBERT base model')
+            urllib.request.urlretrieve(download_url, install_file)
+            print('Downloaded HuBERT')
+        return install_file
+
+
+    @staticmethod
+    def make_sure_tokenizer_installed(model: str = 'quantifier_hubert_base_ls960_14.pth', repo: str = 'GitMylo/bark-voice-cloning', local_file: str = 'tokenizer.pth'):
+        install_dir = os.path.join('data', 'models', 'hubert')
+        if not os.path.isdir(install_dir):
+            os.makedirs(install_dir, exist_ok=True)
+        install_file = os.path.join(install_dir, local_file)
+        if not os.path.isfile(install_file):
+            print('Downloading HuBERT custom tokenizer')
+            huggingface_hub.hf_hub_download(repo, model, local_dir=install_dir, local_dir_use_symlinks=False)
+            shutil.move(os.path.join(install_dir, model), install_file)
+            print('Downloaded tokenizer')
+        return install_file