Upload 3 files

README.md

@@ -1,13 +1,14 @@
 ---
-title: Quantum STT-V1
-emoji: 🐠
-colorFrom: pink
-colorTo: green
+title: Quantum_Speach_Recognizer
+emoji: 🏆
+colorFrom: red
+colorTo: pink
 sdk: gradio
 sdk_version: 5.23.3
 app_file: app.py
-pinned: false
+pinned: true
 license: apache-2.0
+short_description: Speach To Text
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import pipeline
+import os
+
+# Model ID from Hugging Face
+model_id = "sbapan41/Quantum_STT"
+
+# Load the speech recognition pipeline
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model_id,
+    generate_kwargs={"language": "en", "task": "transcribe"},
+    tokenizer=model_id
+)
+
+# Transcription function with format check
+def transcribe(audio):
+    if audio is None:
+        return "Please upload an audio file."
+
+    # Optional: validate file extension
+    ext = os.path.splitext(audio)[1].lower()
+    if ext not in [".caf", ".au", ".opus", ".amr", ".alac", ".aiff", ".wma", ".m4a", ".ogg", ".aac", ".flac", ".wav", ".mp3"]:
+        return f"❌ Unsupported file format: {ext}. Please upload .caf, .au, .opus, .amr, .alac, .aiff, .wma, .m4a, .ogg, .aac, .flac, .wav or .mp3 files."
+
+    result = pipe(audio)
+    return result["text"]
+
+# Gradio interface
+interface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(
+        type="filepath",           # return audio file path
+        sources=["upload"],        # restrict to file upload (not mic)
+        label="🎵 Upload Audio File"
+    ),
+    outputs=gr.Textbox(label="📝 Transcription"),
+    title="🎙️ Quantum Speech Recognizer",
+    description="Upload an audio file (.caf, .au, .opus, .amr, .alac, .aiff, .wma, .m4a, .ogg, .aac, .flac, .wav, .mp3)<br>***to transcribe it using the Quantum_STT model***."
+)
+
+# Launch the interface
+interface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio>=4.0.0
+transformers==4.37.2
+torch>=2.0.0
+torchaudio
+accelerate>=0.21.0