Create app.py

app.py

@@ -0,0 +1,139 @@
+import 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
+
+# Set device
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+
+# Load Mini model and associated components
+repo_id = "TArtx/parler-tts-mini-v1-finetuned-12"
+model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
+
+# Constants
+SAMPLE_RATE = feature_extractor.sampling_rate
+SEED = 42
+
+# Default input text and description
+default_text = "This is a demonstration of my ability to convert written words into spoken language, seamlessly and naturally. As a text-to-speech model, my goal is to sound as clear and engaging as a human, making sure every word I say leaves an impression."
+default_description = "moderate speed, very clear, monotone, wonderful speech quality"
+
+# Number normalizer
+number_normalizer = EnglishNumberNormalizer()
+
+# Preprocessing function
+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(".", "")
+        return " ".join(chunk)
+
+    abbreviations = re.findall(abbreviations_pattern, text)
+    for abv in abbreviations:
+        if abv in text:
+            text = text.replace(abv, separate_abb(abv))
+    return text
+
+# TTS generation function
+def gen_tts(text, description):
+    inputs = tokenizer(description.strip(), 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,
+        attention_mask=inputs.attention_mask,
+        prompt_attention_mask=prompt.attention_mask,
+        do_sample=True,
+        temperature=1.0,
+    )
+    audio_arr = generation.cpu().numpy().squeeze()
+    return SAMPLE_RATE, audio_arr
+
+# CSS for styling
+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;
+        }
+"""
+
+# Gradio interface
+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 demo uses the Mini v1 model by default.</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=default_description, 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")
+
+    inputs = [input_text, description]
+    outputs = [audio_out]
+    run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
+
+# Launch the interface
+block.queue()
+block.launch(share=True)