1st Commit

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,8 +1,8 @@
 ---
 title: ASR Hindi
 emoji: 📉
-colorFrom: red
-colorTo: pink
+colorFrom: yellow
+colorTo: yellow
 sdk: gradio
 sdk_version: 4.38.1
 app_file: app.py

app.py

@@ -0,0 +1,49 @@
+from transformers import pipeline
+import gradio as gr
+import os
+
+model_id = "HarshitJoshi/whisper-small-Hindi"  
+pipe = pipeline("automatic-speech-recognition", model=model_id)
+
+def transcribe_speech(filepath):
+    output = pipe(
+        filepath,
+        max_new_tokens=256,
+        generate_kwargs={
+            "task": "transcribe",
+            "language": "hindi",  
+        },
+        chunk_length_s=30,
+        batch_size=8,
+    )
+    return output["text"]
+
+example_folder = "./examples"  
+example_files = [f for f in os.listdir(example_folder) if f.endswith('.wav') or f.endswith('.mp3')]
+
+demo = gr.Blocks()
+
+mic_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=gr.Textbox(),
+)
+
+file_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs=gr.Textbox(),
+)
+
+example_transcribe = gr.Interface(
+    fn=lambda filename: transcribe_speech(os.path.join(example_folder, filename)),
+    inputs=gr.Dropdown(choices=example_files, label="Select an example"),
+    outputs=gr.Textbox(),
+)
+
+with demo:
+    gr.TabbedInterface(
+        [mic_transcribe, file_transcribe, example_transcribe],
+        ["Transcribe Microphone", "Transcribe Audio File", "Transcribe Example"],
+    )
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+gradio