{
"cells": [
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"output": {
"id": 1352671522828979,
"loadingStatus": "loaded"
}
},
"outputs": [],
"source": [
"import torch\n",
"from IPython.display import Audio, Video\n",
"\n",
"from sam_audio import SAMAudio, SAMAudioProcessor"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"output": {
"id": 885916534002331,
"loadingStatus": "loaded"
}
},
"outputs": [],
"source": [
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"model = SAMAudio.from_pretrained(\"facebook/sam-audio-large\").to(device).eval()\n",
"processor = SAMAudioProcessor.from_pretrained(\"facebook/sam-audio-large\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"output": {
"id": 1281362027072041,
"loadingStatus": "loaded"
}
},
"outputs": [
{
"data": {
"text/html": [
""
],
"text/plain": [
""
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"video_file = \"assets/office.mp4\"\n",
"Video(video_file, embed=True, width=640, height=360)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"inputs = processor(audios=[video_file], descriptions=[\"A man speaking\"]).to(device)\n",
"with torch.inference_mode():\n",
" result = model.separate(inputs)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"Audio(result.target[0].cpu(), rate=processor.audio_sampling_rate)"
]
}
],
"metadata": {
"fileHeader": "",
"fileUid": "8f909f1e-e114-4e58-8c41-a7e2effd92ae",
"isAdHoc": false,
"kernelspec": {
"display_name": "sam-audio",
"language": "python",
"name": "sam-audio"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 4
}