v0.10.1 (#2242)

* Add Ukrainian LADA (female) voice

* Add ca and fa models

* Add pth files to manager

* Bump up to v0.10.1

Co-authored-by: Yehor Smoliakov <yehors@ukr.net>

TTS/.models.json

@@ -617,6 +617,30 @@
                     "license": "bsd-3-clause"
                 }
             }
+        },
+        "ca": {
+            "custom": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.1_models/tts_models--ca--custom--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "description": " It is trained from zero with 101460 utterances consisting of 257 speakers, approx 138 hours of speech. We used three datasets;\nFestcat and Google Catalan TTS (both TTS datasets) and also a part of Common Voice 8. It is trained with TTS v0.8.0.\nhttps://github.com/coqui-ai/TTS/discussions/930#discussioncomment-4466345",
+                    "author": "@gullabi",
+                    "license": "CC-BY-4.0"
+                }
+            }
+        },
+        "fa":{
+            "custom":{
+                "glow-tts": {
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.1_models/tts_models--fa--custom--glow-tts.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "description": "persian-tts-female-glow_tts model for text to speech purposes. Single-speaker female voice Trained on persian-tts-dataset-famale. \nThis model has no compatible vocoder thus the output quality is not very good. \nDataset: https://www.kaggle.com/datasets/magnoliasis/persian-tts-dataset-famale.",
+                    "author": "@karim23657",
+                    "license": "CC-BY-4.0"
+                }
+            }
         }
     },
     "vocoder_models": {

TTS/VERSION

@@ -1 +1 @@
-0.10.0
+0.10.1

TTS/utils/manage.py

@@ -298,7 +298,9 @@ class ModelManager(object):
         """
         output_stats_path = os.path.join(output_path, "scale_stats.npy")
         output_d_vector_file_path = os.path.join(output_path, "speakers.json")
+        output_d_vector_file_pth_path = os.path.join(output_path, "speakers.pth")
         output_speaker_ids_file_path = os.path.join(output_path, "speaker_ids.json")
+        output_speaker_ids_file_pth_path = os.path.join(output_path, "speaker_ids.pth")
         speaker_encoder_config_path = os.path.join(output_path, "config_se.json")
         speaker_encoder_model_path = self._find_speaker_encoder(output_path)
 
@@ -307,11 +309,15 @@ class ModelManager(object):
 
         # update the speakers.json file path in the model config.json to the current path
         self._update_path("d_vector_file", output_d_vector_file_path, config_path)
+        self._update_path("d_vector_file", output_d_vector_file_pth_path, config_path)
         self._update_path("model_args.d_vector_file", output_d_vector_file_path, config_path)
+        self._update_path("model_args.d_vector_file", output_d_vector_file_pth_path, config_path)
 
         # update the speaker_ids.json file path in the model config.json to the current path
         self._update_path("speakers_file", output_speaker_ids_file_path, config_path)
+        self._update_path("speakers_file", output_speaker_ids_file_pth_path, config_path)
         self._update_path("model_args.speakers_file", output_speaker_ids_file_path, config_path)
+        self._update_path("model_args.speakers_file", output_speaker_ids_file_pth_path, config_path)
 
         # update the speaker_encoder file path in the model config.json to the current path
         self._update_path("speaker_encoder_model_path", speaker_encoder_model_path, config_path)

docs/source/tts_datasets.md

@@ -12,5 +12,6 @@ Some of the known public datasets that we successfully applied 🐸TTS:
 - [German - Thorsten OGVD](https://github.com/thorstenMueller/deep-learning-german-tts)
 - [Japanese - Kokoro](https://www.kaggle.com/kaiida/kokoro-speech-dataset-v11-small/version/1)
 - [Chinese](https://www.data-baker.com/data/index/source/)
+- [Ukrainian - LADA](https://github.com/egorsmkv/ukrainian-tts-datasets/tree/main/lada)
 
 Let us know if you use 🐸TTS on a different dataset.