Upload 4 files

README.md

@@ -1,13 +1,14 @@
 ---
-title: Really Fast Whisper
-emoji: 🌖
-colorFrom: blue
-colorTo: green
+title: Blazing Fast Whisper
+emoji: 👁
+colorFrom: gray
+colorTo: yellow
 sdk: gradio
 sdk_version: 5.25.2
 app_file: app.py
 pinned: false
 license: mit
+short_description: Blazing Fast Whisper Deployed on HF Inference Endpoints
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,71 @@
+import os
+from pathlib import Path
+from httpx import AsyncClient
+
+import gradio as gr
+import numpy as np
+from dotenv import load_dotenv
+from fastrtc import (
+    AdditionalOutputs,
+    ReplyOnPause,
+    Stream,
+    audio_to_bytes,
+    get_turn_credentials_async,
+    get_turn_credentials,
+)
+from gradio.utils import get_space
+
+cur_dir = Path(__file__).parent
+
+load_dotenv()
+
+
+client = AsyncClient()
+
+
+async def transcribe(audio: tuple[int, np.ndarray], transcript: str):
+    response = await client.post(
+        url="https://douatiz8x2itm3yn.us-east-1.aws.endpoints.huggingface.cloud/api/v1/audio/transcriptions",
+        headers={"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"},
+        files={"file": audio_to_bytes(audio)},
+        data={
+            "response_format": "text",
+        },
+    )
+    yield AdditionalOutputs(transcript + " " + response.text)
+
+
+transcript = gr.Textbox(label="Transcript")
+stream = Stream(
+    ReplyOnPause(transcribe),
+    modality="audio",
+    mode="send",
+    additional_inputs=[transcript],
+    additional_outputs=[transcript],
+    additional_outputs_handler=lambda a, b: b,
+    rtc_configuration=get_turn_credentials_async if get_space() else None,
+    server_rtc_configuration=get_turn_credentials(ttl=604_800),
+    concurrency_limit=20 if get_space() else None,
+    time_limit=300,
+    ui_args={"title": ""},
+)
+
+with gr.Blocks() as demo:
+    gr.HTML(
+    """
+        <h1 style='text-align: center; display: flex; align-items: center; justify-content: center;'>
+        <img src="/gradio_api/file=AV_Huggy.png" alt="Streaming Huggy" style="height: 50px; margin-right: 10px"> Really Fast Whisper
+        </h1>
+    """
+    )
+    gr.HTML(
+        """
+    <h2 style='text-align: center'>
+    Powered by <a href="https://huggingface.co/hfendpoints/whisper-large-v3">HF Inference Endpoints</a> and <a href="https://fastrtc.org/">FastRTC</a>
+    </h2>
+    """
+    )
+    stream.ui.render()
+
+if __name__ == "__main__":
+    demo.launch(allowed_paths=["AV_Huggy.png"])

requirements.txt

@@ -0,0 +1,2 @@
+fastrtc[vad]==0.0.22.rc2
+python-dotenv