Add neon models (#2140)

* Add neon ljspeech vits model

* Add neon german model

* Update .models.json

* Add neon spanish model

* Add french model

* Add Dutch model

* Add Hungarian model

* Add Greek model

* Remove uneeded description

* Update .models.json

* Update .models.json

* Handling neon models

* Add all neon models

* Update .models.json

* Split zoo_tests

* Update test names

* Update model testing

Co-authored-by: Eren Gölge <erogol@hotmail.com>

.github/workflows/zoo_tests0.yml

@@ -0,0 +1,52 @@
+name: zoo-tests-0
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    types: [opened, synchronize, reopened]
+jobs:
+  check_skip:
+    runs-on: ubuntu-latest
+    if: "! contains(github.event.head_commit.message, '[ci skip]')"
+    steps:
+      - run: echo "${{ github.event.head_commit.message }}"
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.7, 3.8, 3.9, "3.10"]
+        experimental: [false]
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+          cache: 'pip'
+          cache-dependency-path: 'requirements*'
+      - name: check OS
+        run: cat /etc/os-release
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y git make gcc
+          sudo apt-get install espeak espeak-ng
+          make system-deps
+      - name: Install/upgrade Python setup deps
+        run: python3 -m pip install --upgrade pip setuptools wheel
+      - name: Replace scarf urls
+        run: |
+          sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
+      - name: Install TTS
+        run: |
+          python3 -m pip install .[all]
+          python3 setup.py egg_info
+      - name: Unit tests
+        run: |
+          nose2 -F -v -B TTS tests.zoo_tests.test_models.test_models_offset_0_step_3
+          nose2 -F -v -B TTS tests.zoo_tests.test_models.test_voice_conversion

.github/workflows/zoo_tests1.yml

@@ -1,4 +1,4 @@
-name: zoo-tests
+name: zoo-tests-1
 
 on:
   push:
@@ -47,4 +47,4 @@ jobs:
           python3 -m pip install .[all]
           python3 setup.py egg_info
       - name: Unit tests
-        run: make test_zoo
+        run: nose2 -F -v -B --with-coverage --coverage TTS tests.zoo_tests.test_models.test_models_offset_1_step_3

.github/workflows/zoo_tests2.yml

@@ -0,0 +1,50 @@
+name: zoo-tests-2
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    types: [opened, synchronize, reopened]
+jobs:
+  check_skip:
+    runs-on: ubuntu-latest
+    if: "! contains(github.event.head_commit.message, '[ci skip]')"
+    steps:
+      - run: echo "${{ github.event.head_commit.message }}"
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.7, 3.8, 3.9, "3.10"]
+        experimental: [false]
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+          cache: 'pip'
+          cache-dependency-path: 'requirements*'
+      - name: check OS
+        run: cat /etc/os-release
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y git make gcc
+          sudo apt-get install espeak espeak-ng
+          make system-deps
+      - name: Install/upgrade Python setup deps
+        run: python3 -m pip install --upgrade pip setuptools wheel
+      - name: Replace scarf urls
+        run: |
+          sed -i 's/https:\/\/coqui.gateway.scarf.sh\//https:\/\/github.com\/coqui-ai\/TTS\/releases\/download\//g' TTS/.models.json
+      - name: Install TTS
+        run: |
+          python3 -m pip install .[all]
+          python3 setup.py egg_info
+      - name: Unit tests
+        run: nose2 -F -v -B --with-coverage --coverage TTS tests.zoo_tests.test_models.test_models_offset_2_step_3

TTS/.models.json

@@ -12,6 +12,61 @@
                 }
             }
         },
+        "bg": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--bg--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "cs": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--cs--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "da": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--da--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "et": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--et--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "ga": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--ga--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
         "en": {
             "ek1": {
                 "tacotron2": {
@@ -79,6 +134,14 @@
                     "license": "apache 2.0",
                     "contact": "egolge@coqui.com"
                 },
+                "vits--neon": {
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--en--ljspeech--vits.zip",
+                    "default_vocoder": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause",
+                    "contact": null,
+                    "commit": null
+                },   
                 "fast_pitch": {
                     "description": "FastPitch model trained on LJSpeech using the Aligner Network",
                     "github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--fast_pitch.zip",
@@ -151,6 +214,15 @@
                     "license": "MPL",
                     "contact": "egolge@coqui.com"
                 }
+            },
+            "css10":{
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--es--css10--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
             } 
         },
         "fr": {
@@ -158,11 +230,20 @@
                 "tacotron2-DDC": {
                     "github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--fr--mai--tacotron2-DDC.zip",
                     "default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan",
-                    "commit": "",
+                    "commit": null,
                     "author": "Eren Gölge @erogol",
                     "license": "MPL",
                     "contact": "egolge@coqui.com"
                 }
+            },
+            "css10":{
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--fr--css10--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
             }
         },
         "uk":{
@@ -174,6 +255,13 @@
                     "license": "MIT",
                     "contact": "",
                     "default_vocoder": "vocoder_models/uk/mai/multiband-melgan"
+                },
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--uk--mai--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
                 }
             }
         },
@@ -198,6 +286,15 @@
                     "stats_file": null,
                     "commit": "540d811"
                 }
+            },
+            "css10":{
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--nl--css10--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
             }
         },
         "de": {
@@ -224,6 +321,15 @@
                     "license": "apache 2.0",
                     "commit": "unknown"
                 }
+            },
+            "css10": {
+                "vits-neon":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--de--css10--vits.zip",
+                    "default_vocoder": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause",
+                    "commit": null
+                }
             }
         },
         "ja": {
@@ -359,6 +465,149 @@
                     "commit": "1b22f03"
                 }
             }
+        },
+        "hu": {
+            "css10": {
+                "vits": {
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--hu--css10--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "el": {
+            "cv": {
+                "vits": {
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--el--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "fi": {
+            "css10": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--fi--css10--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "hr": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--hr--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "lt": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--lt--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "lv": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--lv--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "mt": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--mt--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "pl": {
+            "mai_female": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--pl--mai_female--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "pt": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--pt--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "ro": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--ro--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "sk": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sk--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "sl": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sl--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
+        },
+        "sv": {
+            "cv": {
+                "vits":{
+                    "github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sv--cv--vits.zip",
+                    "default_vocoder": null,
+                    "commit": null,
+                    "author": "@NeonGeckoCom",
+                    "license": "bsd-3-clause"
+                }
+            }
         }
     },
     "vocoder_models": {

TTS/utils/synthesizer.py

@@ -213,7 +213,12 @@ class Synthesizer(object):
         speaker_embedding = None
         speaker_id = None
         if self.tts_speakers_file or hasattr(self.tts_model.speaker_manager, "name_to_id"):
-            if speaker_name and isinstance(speaker_name, str):
+
+            # handle Neon models with single speaker.
+            if len(self.tts_model.speaker_manager.name_to_id) == 1:
+                speaker_id = list(self.tts_model.speaker_manager.name_to_id.values())[0]
+
+            elif speaker_name and isinstance(speaker_name, str):
                 if self.tts_config.use_d_vector_file:
                     # get the average speaker embedding from the saved d_vectors.
                     speaker_embedding = self.tts_model.speaker_manager.get_mean_embedding(
@@ -243,7 +248,11 @@ class Synthesizer(object):
         if self.tts_languages_file or (
             hasattr(self.tts_model, "language_manager") and self.tts_model.language_manager is not None
         ):
-            if language_name and isinstance(language_name, str):
+
+            if len(self.tts_model.language_manager.name_to_id) == 1:
+                language_id = list(self.tts_model.language_manager.name_to_id.values())[0]
+
+            elif language_name and isinstance(language_name, str):
                 language_id = self.tts_model.language_manager.name_to_id[language_name]
 
             elif not language_name:

tests/zoo_tests/test_models.py

@@ -10,14 +10,13 @@ from TTS.utils.generic_utils import get_user_data_dir
 from TTS.utils.manage import ModelManager
 
 
-def test_run_all_models():
+def run_models(offset=0, step=1):
     """Check if all the models are downloadable and tts models run correctly."""
     print(" > Run synthesizer with all the models.")
-    download_dir = get_user_data_dir("tts")
     output_path = os.path.join(get_tests_output_path(), "output.wav")
     manager = ModelManager(output_prefix=get_tests_output_path(), progress_bar=False)
     model_names = manager.list_models()
-    for model_name in model_names:
+    for model_name in model_names[offset::step]:
         print(f"\n > Run - {model_name}")
         model_path, _, _ = manager.download_model(model_name)
         if "tts_models" in model_name:
@@ -50,15 +49,27 @@ def test_run_all_models():
                     f'--text "This is an example." --out_path "{output_path}" --progress_bar False'
                 )
             # remove downloaded models
-            shutil.rmtree(download_dir)
+            shutil.rmtree(local_download_dir)
+            shutil.rmtree(get_user_data_dir("tts"))
         else:
             # only download the model
             manager.download_model(model_name)
         print(f" | > OK: {model_name}")
 
-    folders = glob.glob(os.path.join(manager.output_prefix, "*"))
+    # folders = glob.glob(os.path.join(manager.output_prefix, "*"))
-    assert len(folders) == len(model_names)
+    # assert len(folders) == len(model_names) // step
-    shutil.rmtree(manager.output_prefix)
+
+
+def test_models_offset_0_step_3():
+    run_models(offset=0, step=3)
+
+
+def test_models_offset_1_step_3():
+    run_models(offset=1, step=3)
+
+
+def test_models_offset_2_step_3():
+    run_models(offset=2, step=3)
 
 
 def test_voice_conversion():