Update app.py

app.py

@@ -4,66 +4,62 @@ import torchaudio
 import gradio as gr
 import spaces
 from transformers import AutoModel
-
+#indicconformer
 DESCRIPTION = "IndicConformer-600M Multilingual ASR (CTC + RNNT)"
+
 LANGUAGE_NAME_TO_CODE = {
-    "Assamese": "as", "Bengali": "bn", "Bodo": "brx", "Dogri": "doi", "Gujarati": "gu", "Hindi": "hi", "Kannada": "kn", "Kashmiri": "ks",
-    "Konkani": "kok", "Maithili": "mai", "Malayalam": "ml", "Manipuri": "mni", "Marathi": "mr", "Nepali": "ne", "Odia": "or", "Punjabi": "pa",
-    "Sanskrit": "sa", "Santali": "sat", "Sindhi": "sd", "Tamil": "ta", "Telugu": "te", "Urdu": "ur"
+    "Assamese": "as", "Bengali": "bn", "Bodo": "brx", "Dogri": "doi",
+    "Gujarati": "gu", "Hindi": "hi", "Kannada": "kn", "Kashmiri": "ks",
+    "Konkani": "kok", "Maithili": "mai", "Malayalam": "ml", "Manipuri": "mni",
+    "Marathi": "mr", "Nepali": "ne", "Odia": "or", "Punjabi": "pa",
+    "Sanskrit": "sa", "Santali": "sat", "Sindhi": "sd", "Tamil": "ta",
+    "Telugu": "te", "Urdu": "ur"
 }
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load Indic Conformer model (assumes custom forward handles decoding strategy)
 model = AutoModel.from_pretrained("ai4bharat/indic-conformer-600m-multilingual", trust_remote_code=True).to(device)
 model.eval()
 
-def chunk_waveform(waveform, sr, max_length_sec=60):
-    num_samples = waveform.shape[1]
-    chunk_length = int(max_length_sec * sr)
-    chunks = []
-    for start in range(0, num_samples, chunk_length):
-        end = min(start + chunk_length, num_samples)
-        chunks.append(waveform[:, start:end])
-    return chunks
-
 @spaces.GPU
 def transcribe_ctc_and_rnnt(audio_path, language_name):
     lang_code = LANGUAGE_NAME_TO_CODE[language_name]
+
+    # Load and preprocess audio
     waveform, sr = torchaudio.load(audio_path)
     waveform = waveform.mean(dim=0, keepdim=True) if waveform.shape[0] > 1 else waveform
     waveform = torchaudio.functional.resample(waveform, sr, 16000).to(device)
-    sr = 16000
 
     try:
-        chunks = chunk_waveform(waveform, sr, max_length_sec=60)  # 60s chunks
-        ctc_transcripts, rnnt_transcripts = [], []
+        # Assume model's forward method takes waveform, language code, and decoding type
         with torch.no_grad():
-            for chunk in chunks:
-                if chunk.shape[1] < sr:  # skip too short segments if needed
-                    continue
-                t_ctc = model(chunk, lang_code, "ctc")
-                t_rnnt = model(chunk, lang_code, "rnnt")
-                ctc_transcripts.append(str(t_ctc).strip())
-                rnnt_transcripts.append(str(t_rnnt).strip())
-
-        ctc_full = " ".join(ctc_transcripts)
-        rnnt_full = " ".join(rnnt_transcripts)
-        return ctc_full, rnnt_full
+            transcription_ctc = model(waveform, lang_code, "ctc")
+            transcription_rnnt = model(waveform, lang_code, "rnnt")
     except Exception as e:
         return f"Error: {str(e)}", ""
 
+    return transcription_ctc.strip(), transcription_rnnt.strip()
+
+# Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown(f"## {DESCRIPTION}")
     with gr.Row():
         with gr.Column():
             audio = gr.Audio(label="Upload or Record Audio", type="filepath")
-            lang = gr.Dropdown(label="Select Language", choices=list(LANGUAGE_NAME_TO_CODE.keys()), value="Hindi")
+            lang = gr.Dropdown(
+                label="Select Language",
+                choices=list(LANGUAGE_NAME_TO_CODE.keys()),
+                value="Hindi"
+            )
             transcribe_btn = gr.Button("Transcribe (CTC + RNNT)")
         with gr.Column():
             gr.Markdown("### CTC Transcription")
-            ctc_output = gr.Textbox(lines=5)
+            ctc_output = gr.Textbox(lines=3)
             gr.Markdown("### RNNT Transcription")
-            rnnt_output = gr.Textbox(lines=5)
+            rnnt_output = gr.Textbox(lines=3)
+
     transcribe_btn.click(fn=transcribe_ctc_and_rnnt, inputs=[audio, lang], outputs=[ctc_output, rnnt_output], api_name="transcribe")
 
 if __name__ == "__main__":
-    demo.queue().launch()
+    demo.queue().launch()