Upload app.py

app.py

@@ -0,0 +1,53 @@
+import torch
+import gradio as gr
+from transformers import pipeline
+from huggingface_hub import model_info
+
+MODEL_NAME = "kurianbenoy/whisper-small-ml-imasc" #this always needs to stay in line 8 :D sorry for the hackiness
+lang = "ml"
+
+device = 0 if torch.cuda.is_available() else "cpu"
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=30,
+    device=device,
+    batch_size=8,
+)
+
+pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
+
+def transcribe(microphone=None, file_upload=None):
+    warn_output = ""
+    if (microphone is not None) and (file_upload is not None):
+        warn_output = (
+            "WARNING: You've uploaded an audio file and used the microphone. "
+            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
+        )
+
+    elif (microphone is None) and (file_upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    file = microphone if microphone is not None else file_upload
+
+    text = pipe(file)["text"]
+
+    return warn_output + text
+
+def transcribe1(file):
+    text = pipe(file)["text"]
+    print(text)
+    return text
+
+#print(transcribe(None,"anil.wav"))
+
+mf_transcribe = gr.Interface(
+    fn=transcribe1,
+    inputs=[
+        gr.Audio(sources=["upload"], type="filepath")
+    ],
+    outputs="text",
+    title="PALLAKKU - Whisper finetuned",
+)
+
+mf_transcribe.launch(debug=True,share=False)