Update app.py

app.py

@@ -1,51 +1,70 @@
 import gradio as gr
-import torch
-import torchaudio
-from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-from huggingface_hub import InferenceClient
+import edge_tts
+import asyncio
+import tempfile
+import os
 
-# Load ASR model
-asr_model_name = "Futuresony/Future-sw_ASR-24-02-2025"
-processor = Wav2Vec2Processor.from_pretrained(asr_model_name)
-asr_model = Wav2Vec2ForCTC.from_pretrained(asr_model_name)
+# Get all available voices
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
-# Load text generation client
-client = InferenceClient("unsloth/gemma-3-1b-it")
+# Text-to-speech function
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter text to convert.")
+    if not voice:
+        return None, gr.Warning("Please select a voice.")
+    
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
 
-# Function: Transcribe audio
-def transcribe(audio_file):
-    waveform, sample_rate = torchaudio.load(audio_file)
-    resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)
-    waveform = resampler(waveform).squeeze().numpy()
-    inputs = processor(waveform, sampling_rate=16000, return_tensors="pt")
-    with torch.no_grad():
-        logits = asr_model(inputs.input_values).logits
-    predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = processor.batch_decode(predicted_ids)[0]
-    return transcription
+# Gradio interface function
+def tts_interface(text, voice, rate, pitch):
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    return audio, warning
 
-# Function: Generate response based on transcription
-def generate_text(prompt):
-    response = client.text_generation(prompt, max_new_tokens=150, temperature=0.7)
-    return response.strip()
-
-# Gradio interface
-def asr_and_generate(audio):
-    if not audio:
-        return "No audio provided.", ""
-    transcription = transcribe(audio)
-    generated = generate_text(transcription)
-    return transcription, generated
+# Create Gradio application
+import gradio as gr
 
-demo = gr.Interface(
-    fn=asr_and_generate,
-    inputs=gr.Audio(label="Upload or Record Audio", type="filepath"),
-    outputs=[
-        gr.Textbox(label="Transcription"),
-        gr.Textbox(label="AI Response")
-    ],
-    title="ASR to Text Generation",
-    description="Upload audio. The model will transcribe speech to text and generate a response using a fine-tuned text model."
-)
+async def create_demo():
+    voices = await get_voices()
+    
+    description = """
+    Convert text to speech using Microsoft Edge TTS. Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease.
+    
+    
+    
+   
+    """
+    
+    demo = gr.Interface(
+        fn=tts_interface,
+        inputs=[
+            gr.Textbox(label="Input Text", lines=5),
+            gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
+            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Warning", visible=False)
+        ],
+        title="Edge TTS Text-to-Speech",
+        description=description,
+       
+        analytics_enabled=False,
+        allow_flagging="manual"
+    )
+    return demo
 
-demo.launch()
+# Run the application
+if __name__ == "__main__":
+    demo = asyncio.run(create_demo())
+    demo.launch()