Update app.py

app.py

@@ -1,171 +1,61 @@
-import spaces
-import gradio as gr
+mport gradio as gr
 import torch
-from transformers.models.speecht5.number_normalizer import EnglishNumberNormalizer
-from string import punctuation
-import re
-
-
-from parler_tts import ParlerTTSForConditionalGeneration
-from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed
-
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
-
-
-repo_id = "gitgato/tr-xtts"
-
-model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
-tokenizer = AutoTokenizer.from_pretrained(repo_id)
-feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
-
+from datasets import load_dataset
+from transformers import pipeline, SpeechT5Processor, SpeechT5HifiGan, SpeechT5ForTextToSpeech
+
+model_id = "gitgato/tr-xtts"  # update with your model id
+# pipe = pipeline("automatic-speech-recognition", model=model_id)
+model = SpeechT5ForTextToSpeech.from_pretrained(model_id)
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+speaker_embeddings = torch.tensor(embeddings_dataset[7440]["xvector"]).unsqueeze(0)
+
+# checkpoint = "microsoft/speecht5_tts"
+processor = SpeechT5Processor.from_pretrained(model_id)
+
+replacements = [
+    ("à", "a"),
+    ("â", "a"),
+    ("ç", "c"),
+    ("è", "e"),
+    ("ë", "e"),
+    ("î", "i"),
+    ("ï", "i"),
+    ("ô", "o"),
+    ("ù", "u"),
+    ("û", "u"),
+    ("ü", "u"),
+]
 
-SAMPLE_RATE = feature_extractor.sampling_rate
-SEED = 42
 
-default_text = "Por favor sorprendeme y habla"
-examples = [
-    [
-        "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
-        "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone."
-    ],
-    [
-        "'This is the best time of my life, Bartley,' she said happily.",
-        "A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
-    ],
-    [
-        "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
-        "A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
-    ],
-    [
-        "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
-        "A male speaker with a low-pitched voice delivers his words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
-    ],
-]
+title = "Text-to-Speech"
+description = """
+Demo for text-to-speech translation in French. Demo uses [Sandiago21/speecht5_finetuned_facebook_voxpopuli_french](https://huggingface.co/Sandiago21/speecht5_finetuned_facebook_voxpopuli_french) checkpoint, which is based on Microsoft's
+[SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model and is fine-tuned in French Audio dataset
+![Text-to-Speech (TTS)"](https://geekflare.com/wp-content/uploads/2021/07/texttospeech-1200x385.png "Diagram of Text-to-Speech (TTS)")
+"""
 
-number_normalizer = EnglishNumberNormalizer()
 
-def preprocess(text):
-    text = number_normalizer(text).strip()
-    text = text.replace("-", " ")
-    if text[-1] not in punctuation:
-        text = f"{text}."
-    
-    abbreviations_pattern = r'\b[A-Z][A-Z\.]+\b'
-    
-    def separate_abb(chunk):
-        chunk = chunk.replace(".","")
-        print(chunk)
-        return " ".join(chunk)
-    
-    abbreviations = re.findall(abbreviations_pattern, text)
-    for abv in abbreviations:
-        if abv in text:
-            text = text.replace(abv, separate_abb(abv))
+def cleanup_text(text):
+    for src, dst in replacements:
+        text = text.replace(src, dst)
     return text
 
-@spaces.GPU
-def gen_tts(text, description):
-    inputs = tokenizer(description, return_tensors="pt").to(device)
-    prompt = tokenizer(preprocess(text), return_tensors="pt").to(device)
-
-    set_seed(SEED)
-    generation = model.generate(
-        input_ids=inputs.input_ids, prompt_input_ids=prompt.input_ids, do_sample=True, temperature=1.0
-    )
-    audio_arr = generation.cpu().numpy().squeeze()
+def synthesize_speech(text):
+    text = cleanup_text(text)
+    inputs = processor(text=text, return_tensors="pt")
 
-    return SAMPLE_RATE, audio_arr
+    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
 
+    return gr.Audio.update(value=(16000, speech.cpu().numpy()))
 
-css = """
-        #share-btn-container {
-            display: flex;
-            padding-left: 0.5rem !important;
-            padding-right: 0.5rem !important;
-            background-color: #000000;
-            justify-content: center;
-            align-items: center;
-            border-radius: 9999px !important; 
-            width: 13rem;
-            margin-top: 10px;
-            margin-left: auto;
-            flex: unset !important;
-        }
-        #share-btn {
-            all: initial;
-            color: #ffffff;
-            font-weight: 600;
-            cursor: pointer;
-            font-family: 'IBM Plex Sans', sans-serif;
-            margin-left: 0.5rem !important;
-            padding-top: 0.25rem !important;
-            padding-bottom: 0.25rem !important;
-            right:0;
-        }
-        #share-btn * {
-            all: unset !important;
-        }
-        #share-btn-container div:nth-child(-n+2){
-            width: auto !important;
-            min-height: 0px !important;
-        }
-        #share-btn-container .wrap {
-            display: none !important;
-        }
-"""
-with gr.Blocks(css=css) as block:
-    gr.HTML(
-        """
-            <div style="text-align: center; max-width: 700px; margin: 0 auto;">
-              <div
-                style="
-                  display: inline-flex; align-items: center; gap: 0.8rem; font-size: 1.75rem;
-                "
-              >
-                <h1 style="font-weight: 900; margin-bottom: 7px; line-height: normal;">
-                  Parler-TTS 🗣️
-                </h1>
-              </div>
-            </div>
-        """
-    )
-    gr.HTML(
-        f"""
-        <p><a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> is a training and inference library for
-        high-fidelity text-to-speech (TTS) models. The model demonstrated here, <a href="https://huggingface.co/gitgato/tr-XTTS"> Parler-TTS Mini v0.1</a>, 
-        is the first iteration model trained using 10k hours of narrated audiobooks. It generates high-quality speech 
-        with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).</p>
-        <p>Tips for ensuring good generation:
-        <ul>
-            <li>Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise</li>
-            <li>Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech</li>
-            <li>The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt</li>
-        </ul>
-        </p>
-        """
-    )
-    with gr.Row():
-        with gr.Column():
-            input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
-            description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
-            run_button = gr.Button("Generate Audio", variant="primary")
-        with gr.Column():
-            audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out")
+syntesize_speech_gradio = gr.Interface(
+    synthesize_speech,
+    inputs = gr.Textbox(label="Text", placeholder="Type something here..."),
+    outputs=gr.Audio(),
+    examples=["Hola, probando audio."],
+    title=title,
+    description=description,
+).launch()
 
-    inputs = [input_text, description]
-    outputs = [audio_out]
-    gr.Examples(examples=examples, fn=gen_tts, inputs=inputs, outputs=outputs, cache_examples=True)
-    run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
-    gr.HTML(
-        """
-        <p>To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data to 50k hours of speech.
-        The v1 release of the model will be trained on this data, as well as inference optimisations, such as flash attention
-        and torch compile, that will improve the latency by 2-4x. If you want to find out more about how this model was trained and even fine-tune it yourself, check-out the 
-        <a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> repository on GitHub.</p>
-        
-        <p>The Parler-TTS codebase and its associated checkpoints are licensed under <a href='https://github.com/huggingface/parler-tts?tab=Apache-2.0-1-ov-file#readme'> Apache 2.0</a>.</p>
-        """
-    )
 
-block.queue()
-block.launch(share=True)