Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

added requirements.txt #80

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
75 changes: 68 additions & 7 deletions clone_voice.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,20 @@
"cells": [
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/akash/miniconda3/envs/vcloning/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n",
"Downloading: \"https://dl.fbaipublicfiles.com/encodec/v0/encodec_24khz-d7cc33bc.th\" to /home/akash/.cache/torch/hub/checkpoints/encodec_24khz-d7cc33bc.th\n",
"100.0%\n"
]
}
],
"source": [
"from bark.generation import load_codec_model, generate_text_semantic\n",
"from encodec.utils import convert_audio\n",
Expand All @@ -18,9 +29,50 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading HuBERT base model\n",
"Downloaded HuBERT\n",
"Downloading HuBERT custom tokenizer\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading (…)rt_base_ls960_14.pth: 100%|██████████| 104M/104M [00:12<00:00, 8.03MB/s] "
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloaded tokenizer\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/plain": [
"'data/models/hubert/tokenizer.pth'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# From https://github.com/gitmylo/bark-voice-cloning-HuBERT-quantizer\n",
"from hubert.hubert_manager import HuBERTManager\n",
Expand All @@ -31,9 +83,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
]
}
],
"source": [
"# From https://github.com/gitmylo/bark-voice-cloning-HuBERT-quantizer \n",
"# Load HuBERT for semantic tokens\n",
Expand Down Expand Up @@ -246,7 +307,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.8"
"version": "3.10.12"
},
"orig_nbformat": 4
},
Expand Down
18 changes: 15 additions & 3 deletions generate.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,21 @@
"cells": [
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'scipy'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m/home/akash/Projects/Project/bark-with-voice-clone/generate.ipynb Cell 1\u001b[0m line \u001b[0;36m2\n\u001b[1;32m <a href='vscode-notebook-cell:/home/akash/Projects/Project/bark-with-voice-clone/generate.ipynb#W0sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mIPython\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mdisplay\u001b[39;00m \u001b[39mimport\u001b[39;00m Audio\n\u001b[0;32m----> <a href='vscode-notebook-cell:/home/akash/Projects/Project/bark-with-voice-clone/generate.ipynb#W0sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mscipy\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mio\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mwavfile\u001b[39;00m \u001b[39mimport\u001b[39;00m write \u001b[39mas\u001b[39;00m write_wav\n\u001b[1;32m <a href='vscode-notebook-cell:/home/akash/Projects/Project/bark-with-voice-clone/generate.ipynb#W0sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mbark\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mapi\u001b[39;00m \u001b[39mimport\u001b[39;00m generate_audio\n\u001b[1;32m <a href='vscode-notebook-cell:/home/akash/Projects/Project/bark-with-voice-clone/generate.ipynb#W0sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mbark\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mgeneration\u001b[39;00m \u001b[39mimport\u001b[39;00m SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'scipy'"
]
}
],
"source": [
"from IPython.display import Audio\n",
"from scipy.io.wavfile import write as write_wav\n",
Expand Down Expand Up @@ -164,7 +176,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.8"
"version": "3.10.12"
},
"orig_nbformat": 4
},
Expand Down
9 changes: 9 additions & 0 deletions requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
numpy
encodec
funcy
scipy
tqdm
transformers
fairseq
tensorboardX
audiolm_pytorch