Create app.py

app.py

@@ -0,0 +1,188 @@
+import tempfile
+from typing import Optional
+from TTS.config import load_config
+import gradio as gr
+import numpy as np
+from TTS.utils.manage import ModelManager
+from TTS.utils.synthesizer import Synthesizer
+
+# Classe estendida para confirmar automaticamente os termos de uso
+class CustomModelManager(ModelManager):
+    def ask_tos(self, output_path):
+        print("This sentence has been generated by a speech synthesis system. tts_models/multilingual/multi-dataset/xtts_v1.1")
+        print(" > You must confirm the following:")
+        print(' | > "I have purchased a commercial license from Coqui: [email protected]"')
+        print(' | > "Otherwise, I agree to the terms of the non-commercial CPML: https://coqui.ai/cpml" - [y/n]')
+        answer = 'y'  # Automaticamente aceita os termos
+        return answer.lower() == 'y'
+
+# Substituir o gerenciador padrão pelo personalizado
+manager = CustomModelManager()
+MODELS = {}
+SPEAKERS = {}
+MAX_TXT_LEN = 100
+
+MODEL_NAMES = manager.list_tts_models()
+
+# filter out multi-speaker models and slow wavegrad vocoders
+filters = ["vctk", "your_tts", "ek1"]
+MODEL_NAMES = [model_name for model_name in MODEL_NAMES if not any(f in model_name for f in filters)]
+
+EN = [el for el in MODEL_NAMES if "/en/" in el]
+OTHER = [el for el in MODEL_NAMES if "/en/" not in el]
+EN[0], EN[5] = EN[5], EN[0]
+MODEL_NAMES = EN + OTHER
+
+# reorder models
+print(MODEL_NAMES)
+
+
+def tts(text: str, model_name: str):
+    if len(text) > MAX_TXT_LEN:
+        text = text[:MAX_TXT_LEN]
+        print(f"Input text was cutoff since it went over the {MAX_TXT_LEN} character limit.")
+    print(text, model_name)
+    # download model
+    model_path, config_path, model_item = manager.download_model(model_name)
+    print(f"Model path: {model_path}")
+    print(f"Config path: {config_path}")
+    print(f"Model item: {model_item}")
+    
+    if config_path is None and 'config.json' in model_item['hf_url']:
+        config_url = model_item['hf_url'][3]  # Assuming the 4th URL is always the config.json
+        config_path = manager.download_from_url(config_url, model_name)
+        print(f"Downloaded config path: {config_path}")
+
+    if model_path is None or config_path is None:
+        raise ValueError("Model path or config path is None")
+    
+    vocoder_name: Optional[str] = model_item["default_vocoder"]
+    # download vocoder
+    vocoder_path = None
+    vocoder_config_path = None
+    if vocoder_name is not None:
+        vocoder_path, vocoder_config_path, _ = manager.download_model(vocoder_name)
+    
+    # init synthesizer
+    synthesizer = Synthesizer(
+        model_path, config_path, None, None, vocoder_path, vocoder_config_path,
+    )
+    # synthesize
+    if synthesizer is None:
+        raise NameError("model not found")
+    wavs = synthesizer.tts(text, None)
+    # return output
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
+        synthesizer.save_wav(wavs, fp)
+        return fp.name
+
+
+title = """<h1 align="center">🐸💬 CoquiTTS Playground </h1>"""
+
+with gr.Blocks(analytics_enabled=False) as demo:
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown(
+                """
+                ## <img src="https://raw.githubusercontent.com/coqui-ai/TTS/main/images/coqui-log-green-TTS.png" height="56"/>
+                """
+            )
+            gr.Markdown(
+                """
+                <br />
+
+                ## 🐸Coqui.ai News
+                - 📣 ⓍTTS, our production TTS model that can speak 13 languages, is released [Blog Post](https://coqui.ai/blog/tts/open_xtts), [Demo](https://huggingface.co/spaces/coqui/xtts), [Docs](https://tts.readthedocs.io/en/dev/models/xtts.html)
+                - 📣 [🐶Bark](https://github.com/suno-ai/bark) is now available for inference with unconstrained voice cloning. [Docs](https://tts.readthedocs.io/en/dev/models/bark.html)
+                - 📣 You can use [~1100 Fairseq models](https://github.com/facebookresearch/fairseq/tree/main/examples/mms) with 🐸TTS.
+                - 📣 🐸TTS now supports 🐢Tortoise with faster inference. [Docs](https://tts.readthedocs.io/en/dev/models/tortoise.html)
+                - 📣 **Coqui Studio API** is landed on 🐸TTS. - [Example](https://github.com/coqui-ai/TTS/blob/dev/README.md#-python-api)
+                - 📣 [**Coqui Studio API**](https://docs.coqui.ai/docs) is live.
+                - 📣 Voice generation with prompts - **Prompt to Voice** - is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin)!! - [Blog Post](https://coqui.ai/blog/tts/prompt-to-voice)
+                - 📣 Voice generation with fusion - **Voice fusion** - is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin).
+                - 📣 Voice cloning is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin).
+                <br>
+
+                """
+                )
+        with gr.Column():
+            gr.Markdown(
+            """
+            <br/>
+
+            💻 This space showcases some of the **[CoquiTTS](https://github.com/coqui-ai/TTS)** models.
+
+            <br/>
+
+            There are > 30 languages with single and multi speaker models, all thanks to our 👑 Contributors.
+
+            <br/>
+
+            Visit the links below for more.
+
+            |                                 |                                         |
+            | ------------------------------- | --------------------------------------- |
+            | 🐸💬 **CoquiTTS**                |  [Github](https://github.com/coqui-ai/TTS) |
+            | 💼 **Documentation**            | [ReadTheDocs](https://tts.readthedocs.io/en/latest/)
+            | 👩‍💻 **Questions**                | [GitHub Discussions] |
+            | 🗯 **Community**         | [![Dicord](https://img.shields.io/discord/1037326658807533628?color=%239B59B6&label=chat%20on%20discord)](https://discord.gg/5eXr5seRrv)  |
+
+            [github issue tracker]: https://github.com/coqui-ai/tts/issues
+            [github discussions]: https://github.com/coqui-ai/TTS/discussions
+            [discord]: https://discord.gg/5eXr5seRrv
+
+
+            """
+            )
+
+    with gr.Row():
+        gr.Markdown(
+            """
+            <details>
+            <summary>👑 Model contributors</summary>
+
+            - <a href="https://github.com/nmstoker/" target="_blank">@nmstoker</a>
+            - <a href="https://github.com/kaiidams/" target="_blank">@kaiidams</a>
+            - <a href="https://github.com/WeberJulian/" target="_blank">@WeberJulian,</a>
+            - <a href="https://github.com/Edresson/" target="_blank">@Edresson</a>
+            - <a href="https://github.com/thorstenMueller/" target="_blank">@thorstenMueller</a>
+            - <a href="https://github.com/r-dh/" target="_blank">@r-dh</a>
+            - <a href="https://github.com/kirianguiller/" target="_blank">@kirianguiller</a>
+            - <a href="https://github.com/robinhad/" target="_blank">@robinhad</a>
+            - <a href="https://github.com/fkarabiber/" target="_blank">@fkarabiber</a>
+            - <a href="https://github.com/nicolalandro/" target="_blank">@nicolalandro</a>
+            - <a href="https://github.com/a-froghyar" target="_blank">@a-froghyar</a>
+            - <a href="https://github.com/manmay-nakhashi" target="_blank">@manmay-nakhashi</a>
+            - <a href="https://github.com/noml4u" target="_blank">@noml4u</a>
+            </details>
+
+            <br/>
+            """
+        )
+
+    with gr.Row():
+        with gr.Column():
+            input_text = gr.inputs.Textbox(
+                label="Input Text",
+                default="This sentence has been generated by a speech synthesis system.",
+            )
+            model_select = gr.inputs.Dropdown(
+                label="Pick Model: tts_models/<language>/<dataset>/<model_name>",
+                choices=MODEL_NAMES,
+                default="tts_models/en/jenny/jenny"
+            )
+            tts_button = gr.Button("Send", elem_id="send-btn", visible=True)
+
+        with gr.Column():
+            output_audio = gr.outputs.Audio(label="Output", type="filepath")
+
+    tts_button.click(
+        tts,
+        inputs=[
+            input_text,
+            model_select,
+        ],
+        outputs=[output_audio],
+    )
+
+demo.queue(concurrency_count=16).launch(debug=True)