Initial checkin

app.py

@@ -0,0 +1,50 @@
+import torch
+
+import gradio as gr
+from transformers import pipeline
+from transformers.pipelines.audio_utils import ffmpeg_read
+
+MODEL_NAME = "openai/whisper-large-v3"
+BATCH_SIZE = 8
+FILE_LIMIT_MB = 1000
+YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+
+device = 0 if torch.cuda.is_available() else "cpu"
+
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=30,
+    device=device,
+)
+
+
+def transcribe(inputs):
+    if inputs is None:
+        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
+
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": "transcribe"}, return_timestamps=True)["text"]
+    return  text
+
+
+demo = gr.Blocks()
+
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(sources=["microphone"], type="filepath", scale=4),
+    ],
+    outputs="text",
+    title="Whisper Large V3: Transcribe Audio",
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    )
+)
+
+
+with demo:
+    gr.TabbedInterface([mf_transcribe], ["Microphone"])
+
+demo.launch()

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/huggingface/transformers
+torch