Upload folder using huggingface_hub

requirements.txt

@@ -1,5 +1,5 @@
-gradio-client @ git+https://github.com/gradio-app/gradio@38c2ad425a905431b1eb17b9498669f9e49f0dd5#subdirectory=client/python
-https://gradio-builds.s3.amazonaws.com/38c2ad425a905431b1eb17b9498669f9e49f0dd5/gradio-4.38.1-py3-none-any.whl
+gradio-client @ git+https://github.com/gradio-app/gradio@76c175935019833baef709a5cf401d2263ca72ee#subdirectory=client/python
+https://gradio-builds.s3.amazonaws.com/76c175935019833baef709a5cf401d2263ca72ee/gradio-4.38.1-py3-none-any.whl
 torch
 torchaudio
 transformers

run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: asr"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio torch torchaudio transformers"]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from transformers import pipeline\n", "import numpy as np\n", "\n", "transcriber = pipeline(\"automatic-speech-recognition\", model=\"openai/whisper-base.en\")\n", "\n", "def transcribe(audio):\n", "    sr, y = audio\n", "    y = y.astype(np.float32)\n", "    y /= np.max(np.abs(y))\n", "\n", "    return transcriber({\"sampling_rate\": sr, \"raw\": y})[\"text\"]\n", "\n", "\n", "demo = gr.Interface(\n", "    transcribe,\n", "    gr.Audio(sources=[\"microphone\"]),\n", "    \"text\",\n", ")\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: asr"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio torch torchaudio transformers"]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from transformers import pipeline\n", "import numpy as np\n", "\n", "transcriber = pipeline(\"automatic-speech-recognition\", model=\"openai/whisper-base.en\")\n", "\n", "def transcribe(audio):\n", "    sr, y = audio\n", "    y = y.astype(np.float32)\n", "    y /= np.max(np.abs(y))\n", "\n", "    return transcriber({\"sampling_rate\": sr, \"raw\": y})[\"text\"]  # type: ignore\n", "\n", "\n", "demo = gr.Interface(\n", "    transcribe,\n", "    gr.Audio(sources=[\"microphone\"]),\n", "    \"text\",\n", ")\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

run.py

@@ -9,7 +9,7 @@ def transcribe(audio):
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
-    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]  # type: ignore
 
 
 demo = gr.Interface(