chore: use original instead of scarf urls

These allowed Coqui to get download stats, which we don't need anymore

.github/workflows/tests.yml

@@ -29,10 +29,6 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y --no-install-recommends git make gcc
           make system-deps
-      - name: Replace scarf urls
-        if: contains(fromJSON('["data_tests", "inference_tests", "test_aux", "test_tts", "test_tts2", "test_xtts", "test_zoo0", "test_zoo1", "test_zoo2"]'), matrix.subset)
-        run: |
-          sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
       - name: Unit tests
         run: |
           resolution=highest

TTS/demos/xtts_ft_demo/utils/gpt_train.py

@@ -43,8 +43,8 @@ def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv,
     os.makedirs(CHECKPOINTS_OUT_PATH, exist_ok=True)
 
     # DVAE files
-    DVAE_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/dvae.pth"
-    MEL_NORM_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/mel_stats.pth"
+    DVAE_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/dvae.pth"
+    MEL_NORM_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/mel_stats.pth"
 
     # Set the path to the downloaded files
     DVAE_CHECKPOINT = os.path.join(CHECKPOINTS_OUT_PATH, os.path.basename(DVAE_CHECKPOINT_LINK))
@@ -58,9 +58,9 @@ def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv,
         )
 
     # Download XTTS v2.0 checkpoint if needed
-    TOKENIZER_FILE_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/vocab.json"
-    XTTS_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/model.pth"
-    XTTS_CONFIG_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/config.json"
+    TOKENIZER_FILE_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/vocab.json"
+    XTTS_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/model.pth"
+    XTTS_CONFIG_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/config.json"
 
     # XTTS transfer learning parameters: You we need to provide the paths of XTTS model checkpoint that you want to do the fine tuning.
     TOKENIZER_FILE = os.path.join(CHECKPOINTS_OUT_PATH, os.path.basename(TOKENIZER_FILE_LINK))  # vocab.json file

TTS/tts/layers/tortoise/arch_utils.py

@@ -293,7 +293,7 @@ def forward(self, x):
         return h[:, :, 0]
 
 
-DEFAULT_MEL_NORM_FILE = "https://coqui.gateway.scarf.sh/v0.14.1_models/mel_norms.pth"
+DEFAULT_MEL_NORM_FILE = "https://github.com/coqui-ai/TTS/releases/download/v0.14.1_models/mel_norms.pth"
 
 
 class TorchMelSpectrogram(nn.Module):

TTS/tts/layers/xtts/trainer/gpt_trainer.py

@@ -50,7 +50,7 @@ class GPTArgs(XttsArgs):
     max_wav_length: int = 255995  # ~11.6 seconds
     max_text_length: int = 200
     tokenizer_file: str = ""
-    mel_norm_file: str = "https://coqui.gateway.scarf.sh/v0.14.0_models/mel_norms.pth"
+    mel_norm_file: str = "https://github.com/coqui-ai/TTS/releases/download/v0.14.0_models/mel_norms.pth"
     dvae_checkpoint: str = ""
     xtts_checkpoint: str = ""
     gpt_checkpoint: str = ""  # if defined it will replace the gpt weights on xtts model

TTS/utils/manage.py

@@ -230,7 +230,7 @@ def _download_hf_model(self, model_item: Dict, output_path: str):
             self._download_zip_file(model_item["hf_url"], output_path, self.progress_bar)
 
     def download_fairseq_model(self, model_name, output_path):
-        URI_PREFIX = "https://coqui.gateway.scarf.sh/fairseq/"
+        URI_PREFIX = "https://dl.fbaipublicfiles.com/mms/tts/"
         _, lang, _, _ = model_name.split("/")
         model_download_uri = os.path.join(URI_PREFIX, f"{lang}.tar.gz")
         self._download_tar_file(model_download_uri, output_path, self.progress_bar)
@@ -243,9 +243,9 @@ def set_model_url(model_item: Dict):
         elif "hf_url" in model_item:
             model_item["model_url"] = model_item["hf_url"]
         elif "fairseq" in model_item["model_name"]:
-            model_item["model_url"] = "https://coqui.gateway.scarf.sh/fairseq/"
+            model_item["model_url"] = "https://dl.fbaipublicfiles.com/mms/tts/"
         elif "xtts" in model_item["model_name"]:
-            model_item["model_url"] = "https://coqui.gateway.scarf.sh/xtts/"
+            model_item["model_url"] = "https://huggingface.co/coqui/"
         return model_item
 
     def _set_model_item(self, model_name):
@@ -278,11 +278,11 @@ def _set_model_item(self, model_name):
                 "contact": "[email protected]",
                 "tos_required": True,
                 "hf_url": [
-                    f"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/{model_version}/model.pth",
-                    f"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/{model_version}/config.json",
-                    f"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/{model_version}/vocab.json",
-                    f"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/{model_version}/hash.md5",
-                    f"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/{model_version}/speakers_xtts.pth",
+                    f"https://huggingface.co/coqui/XTTS-v2/resolve/{model_version}/model.pth",
+                    f"https://huggingface.co/coqui/XTTS-v2/resolve/{model_version}/config.json",
+                    f"https://huggingface.co/coqui/XTTS-v2/resolve/{model_version}/vocab.json",
+                    f"https://huggingface.co/coqui/XTTS-v2/resolve/{model_version}/hash.md5",
+                    f"https://huggingface.co/coqui/XTTS-v2/resolve/{model_version}/speakers_xtts.pth",
                 ],
             }
         else:

recipes/ljspeech/xtts_v1/train_gpt_xtts.py

@@ -41,8 +41,8 @@
 
 
 # DVAE files
-DVAE_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/dvae.pth"
-MEL_NORM_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/mel_stats.pth"
+DVAE_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v1/resolve/v1.1.2/dvae.pth"
+MEL_NORM_LINK = "https://huggingface.co/coqui/XTTS-v1/resolve/v1.1.2/mel_stats.pth"
 
 # Set the path to the downloaded files
 DVAE_CHECKPOINT = os.path.join(CHECKPOINTS_OUT_PATH, DVAE_CHECKPOINT_LINK.split("/")[-1])
@@ -55,8 +55,8 @@
 
 
 # Download XTTS v1.1 checkpoint if needed
-TOKENIZER_FILE_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/vocab.json"
-XTTS_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/model.pth"
+TOKENIZER_FILE_LINK = "https://huggingface.co/coqui/XTTS-v1/resolve/v1.1.2/vocab.json"
+XTTS_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v1/resolve/v1.1.2/model.pth"
 
 # XTTS transfer learning parameters: You we need to provide the paths of XTTS model checkpoint that you want to do the fine tuning.
 TOKENIZER_FILE = os.path.join(CHECKPOINTS_OUT_PATH, TOKENIZER_FILE_LINK.split("/")[-1])  # vocab.json file

recipes/ljspeech/xtts_v2/train_gpt_xtts.py

@@ -41,8 +41,8 @@
 
 
 # DVAE files
-DVAE_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/dvae.pth"
-MEL_NORM_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/mel_stats.pth"
+DVAE_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/dvae.pth"
+MEL_NORM_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/mel_stats.pth"
 
 # Set the path to the downloaded files
 DVAE_CHECKPOINT = os.path.join(CHECKPOINTS_OUT_PATH, os.path.basename(DVAE_CHECKPOINT_LINK))
@@ -55,8 +55,8 @@
 
 
 # Download XTTS v2.0 checkpoint if needed
-TOKENIZER_FILE_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/vocab.json"
-XTTS_CHECKPOINT_LINK = "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/model.pth"
+TOKENIZER_FILE_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/vocab.json"
+XTTS_CHECKPOINT_LINK = "https://huggingface.co/coqui/XTTS-v2/resolve/main/model.pth"
 
 # XTTS transfer learning parameters: You we need to provide the paths of XTTS model checkpoint that you want to do the fine tuning.
 TOKENIZER_FILE = os.path.join(CHECKPOINTS_OUT_PATH, os.path.basename(TOKENIZER_FILE_LINK))  # vocab.json file