ayo/VibeVoice
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update Colab: add download audio

Browse source
This commit is contained in:
YaoyaoChang 2025-09-02 02:08:19 -07:00
parent 21c35b4701
commit 6065c5224e
1 changed files with 72 additions and 46 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

118
demo/VibeVoice_colab.ipynb
View file

@ -3,8 +3,8 @@
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
@ -12,32 +12,34 @@
},
{
"cell_type": "markdown",
"source": [
"# VibeVoice Colab — T4 Quickstart (1.5B)\n",
"\n",
"This notebook provides a quickstart guide to run VibeVoice on Colab with T4. The T4 GPU can only support the 1.5B model due to memory limitations. Please note that T4 can only use SDPA instead of flash_attention_2, which may result in unstable and lower audio quality. For the best TTS experience, we recommend trying the 7B model on a more powerful GPU.\n",
"\n",
"## Risks and Limitations\n",
"\n",
"While efforts have been made to optimize it through various techniques, it may still produce outputs that are unexpected, biased, or inaccurate. VibeVoice inherits any biases, errors, or omissions produced by its base model (specifically, Qwen2.5 1.5b in this release). Potential for Deepfakes and Disinformation: High-quality synthetic speech can be misused to create convincing fake audio content for impersonation, fraud, or spreading disinformation. Users must ensure transcripts are reliable, check content accuracy, and avoid using generated content in misleading ways. Users are expected to use the generated content and to deploy the models in a lawful manner, in full compliance with all applicable laws and regulations in the relevant jurisdictions. It is best practice to disclose the use of AI when sharing AI-generated content."
],
"id": "WvIaUJD2y0yU",
"metadata": {
"id": "WvIaUJD2y0yU"
},
"id": "WvIaUJD2y0yU"
"source": [
"# VibeVoice Colab — T4 Quickstart (1.5B)\n",
"\n",
"This notebook provides a quickstart guide to run VibeVoice on Colab with T4. The T4 GPU can only support the 1.5B model due to memory limitations. Please note that T4 can only use SDPA instead of flash_attention_2, which may result in unstable and lower audio quality. For the best TTS experience, we recommend trying the 7B model on a more powerful GPU.\n"
]
},
{
"cell_type": "markdown",
"source": [
"## Step 1: Setup Environment"
],
"id": "e8fTKYGx7DZk",
"metadata": {
"id": "e8fTKYGx7DZk"
},
"id": "e8fTKYGx7DZk"
"source": [
"## Step 1: Setup Environment"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4wxJ6QHM-ZOb",
"metadata": {
"id": "4wxJ6QHM-ZOb"
},
"outputs": [],
"source": [
"# Check for T4 GPU\n",
"import torch\n",
@ -70,50 +72,50 @@
"# Download model (~3 minutes)\n",
"!HF_XET_HIGH_PERFORMANCE=1 hf download microsoft/VibeVoice-1.5B --quiet --local-dir /content/models/VibeVoice-1.5B > /dev/null\n",
"print(\"✅ Downloaded model: microsoft/VibeVoice-1.5B\")\n"
],
"metadata": {
"id": "4wxJ6QHM-ZOb"
},
"id": "4wxJ6QHM-ZOb",
"execution_count": null,
"outputs": []
]
},
{
"cell_type": "markdown",
"source": [
"## Step 2: Create Transcript"
],
"id": "pgKlV7153Ifi",
"metadata": {
"id": "pgKlV7153Ifi"
},
"id": "pgKlV7153Ifi"
"source": [
"## Step 2: Create Transcript"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "Yc1N9EHswFxA",
"metadata": {
"id": "Yc1N9EHswFxA"
},
"outputs": [],
"source": [
"%%writefile /content/my_transcript.txt\n",
"Speaker 1: Can I try VibeVoice with my own example?\n",
"Speaker 2: Of course! VibeVoice is open-source, built to benefit everyone - you're welcome to try it out.\n"
],
"metadata": {
"id": "Yc1N9EHswFxA"
},
"id": "Yc1N9EHswFxA",
"execution_count": null,
"outputs": []
]
},
{
"cell_type": "markdown",
"source": [
"## Step 3: Generate Audio"
],
"id": "MBCC6s-F6_hP",
"metadata": {
"id": "MBCC6s-F6_hP"
},
"id": "MBCC6s-F6_hP"
"source": [
"## Step 3: Generate Audio"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dYWsLJ-n0Npm",
"metadata": {
"id": "dYWsLJ-n0Npm"
},
"outputs": [],
"source": [
"# Run Python script to generate audio from transcript\n",
"!python /content/VibeVoice/demo/inference_from_file.py \\\n",
@ -124,23 +126,47 @@
"# Display audio controls\n",
"from IPython.display import Audio\n",
"Audio(\"/content/outputs/my_transcript_generated.wav\")\n"
],
"metadata": {
"id": "dYWsLJ-n0Npm"
},
"id": "dYWsLJ-n0Npm",
]
},
{
"cell_type": "markdown",
"id": "ec6438d5",
"metadata": {},
"source": [
"# Step 4: Download Audio"
]
},
{
"cell_type": "code",
"execution_count": null,
"outputs": []
"id": "b40ffa22",
"metadata": {},
"outputs": [],
"source": [
"from google.colab import files\n",
"files.download(\"/content/outputs/my_transcript_generated.wav\") \n"
]
},
{
"cell_type": "markdown",
"id": "1bce752d",
"metadata": {},
"source": [
"\n",
"## Risks and Limitations\n",
"\n",
"While efforts have been made to optimize it through various techniques, it may still produce outputs that are unexpected, biased, or inaccurate. VibeVoice inherits any biases, errors, or omissions produced by its base model (specifically, Qwen2.5 1.5b in this release). Potential for Deepfakes and Disinformation: High-quality synthetic speech can be misused to create convincing fake audio content for impersonation, fraud, or spreading disinformation. Users must ensure transcripts are reliable, check content accuracy, and avoid using generated content in misleading ways. Users are expected to use the generated content and to deploy the models in a lawful manner, in full compliance with all applicable laws and regulations in the relevant jurisdictions. It is best practice to disclose the use of AI when sharing AI-generated content."
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": [],
"include_colab_link": true,
"machine_shape": "hm",
"name": "VibeVoice_Colab.ipynb",
"include_colab_link": true
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",