Duplicate from coqui/xtts

Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/female.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+title: XTTS
+emoji: 🐸
+colorFrom: green
+colorTo: red
+sdk: gradio
+sdk_version: 3.44.2
+app_file: app.py
+pinned: false
+models:
+- coqui/XTTS-v1
+duplicated_from: coqui/xtts
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,239 @@
+import sys
+import os
+
+import gradio as gr
+from TTS.api import TTS
+
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1")
+tts.to("cuda")
+
+def predict(prompt, language, audio_file_pth, mic_file_path, use_mic, agree):
+    if agree == True:
+        if use_mic == True:
+            if mic_file_path is not None:
+                speaker_wav=mic_file_path
+            else:
+                gr.Warning("Please record your voice with Microphone, or uncheck Use Microphone to use reference audios")
+                return (
+                    None,
+                    None,
+                ) 
+                
+        else:
+            speaker_wav=audio_file_pth
+
+        if len(prompt)<2:
+            gr.Warning("Please give a longer prompt text")
+            return (
+                    None,
+                    None,
+                )
+        try:   
+            tts.tts_to_file(
+                text=prompt,
+                file_path="output.wav",
+                speaker_wav=speaker_wav,
+                language=language,
+            )
+        except RuntimeError as e :
+            if "device-assert" in str(e):
+                # cannot do anything on cuda device side error, need tor estart
+                gr.Warning("Unhandled Exception encounter, please retry in a minute")
+                print("Cuda device-assert Runtime encountered need restart")
+                sys.exit("Exit due to cuda device-assert")
+            else:
+                raise e
+            
+        return (
+            gr.make_waveform(
+                audio="output.wav",
+            ),
+            "output.wav",
+        )
+    else:
+        gr.Warning("Please accept the Terms & Condition!")
+        return (
+                None,
+                None,
+            ) 
+
+
+title = "Coqui🐸 XTTS"
+
+description = """
+<a href="https://huggingface.co/coqui/XTTS-v1">XTTS</a> is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip. 
+<br/>
+XTTS is built on previous research, like Tortoise, with additional architectural innovations and training to make cross-language voice cloning and multilingual speech generation possible. 
+<br/>
+This is the same model that powers our creator application <a href="https://coqui.ai">Coqui Studio</a> as well as the <a href="https://docs.coqui.ai">Coqui API</a>. In production we apply modifications to make low-latency streaming possible.
+<br/>
+Leave a star on the Github <a href="https://github.com/coqui-ai/TTS">🐸TTS</a>, where our open-source inference and training code lives.
+<br/>
+<p>For faster inference without waiting in the queue, you should duplicate this space and upgrade to GPU via the settings.
+<br/>
+<a href="https://huggingface.co/spaces/coqui/xtts?duplicate=true">
+<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
+</p>
+"""
+
+article = """
+<div style='margin:20px auto;'>
+<p>By using this demo you agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml</p>
+</div>
+"""
+examples = [
+    [
+        "Once when I was six years old I saw a magnificent picture",
+        "en",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image",
+        "fr",
+        "examples/male.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Als ich sechs war, sah ich einmal ein wunderbares Bild",
+        "de",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Cuando tenía seis años, vi una vez una imagen magnífica",
+        "es",
+        "examples/male.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Quando eu tinha seis anos eu vi, uma vez, uma imagem magnífica",
+        "pt",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Kiedy miałem sześć lat, zobaczyłem pewnego razu wspaniały obrazek",
+        "pl",
+        "examples/male.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno",
+        "it",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Bir zamanlar, altı yaşındayken, muhteşem bir resim gördüm",
+        "tr",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Когда мне было шесть лет, я увидел однажды удивительную картинку",
+        "ru",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Toen ik een jaar of zes was, zag ik op een keer een prachtige plaat",
+        "nl",
+        "examples/male.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "Když mi bylo šest let, viděl jsem jednou nádherný obrázek",
+        "cs",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+    ],
+]
+
+
+
+gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(
+            label="Text Prompt",
+            info="One or two sentences at a time is better",
+            value="Hi there, I'm your new voice clone. Try your best to upload quality audio. Like my grandma used to say: 'Garbage in, garbage out!'",
+        ),
+        gr.Dropdown(
+            label="Language",
+            info="Select an output language for the synthesised speech",
+            choices=[
+                "en",
+                "es",
+                "fr",
+                "de",
+                "it",
+                "pt",
+                "pl",
+                "tr",
+                "ru",
+                "nl",
+                "cs",
+                "ar",
+                "zh-cn",
+            ],
+            max_choices=1,
+            value="en",
+        ),
+        gr.Audio(
+            label="Reference Audio",
+            info="Click on the ✎ button to upload your own target speaker audio",
+            type="filepath",
+            value="examples/female.wav",
+        ),
+        gr.Audio(source="microphone",
+                 type="filepath",
+                 info="Use your microphone to record audio",
+                 label="Use Microphone for Reference"),
+        gr.Checkbox(label="Check to use Microphone as Reference", value=False),
+        gr.Checkbox(
+            label="Agree",
+            value=False,
+            info="I agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml",
+        ),
+    ],
+    outputs=[
+        gr.Video(label="Waveform Visual"),
+        gr.Audio(label="Synthesised Audio"),
+    ],
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
+).queue().launch(debug=True)

examples/female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a4fa9a16b6463f852cf9424f72c3d3c87aa83010e89db534c53fcd1ae12c02
+size 1002030

examples/male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937c74afad004937e00d1687c68e02210e0c5d93ac072a7c8aeb9ab573517bb1
+size 762126

requirements.txt

@@ -0,0 +1,2 @@
+TTS==0.17.1
+gradio==3.41.2