Install¶
In [1]:
# install bark (make sure you have torch>=2 for much faster flash-attention)
!pip install git+https://github.com/suno-ai/bark.git
Collecting git+https://github.com/suno-ai/bark.git
Cloning https://github.com/suno-ai/bark.git to /tmp/pip-req-build-083hdi07
Running command git clone --filter=blob:none --quiet https://github.com/suno-ai/bark.git /tmp/pip-req-build-083hdi07
Resolved https://github.com/suno-ai/bark.git to commit f4f32d4cd480dfec1c245d258174bc9bde3c2148
Installing build dependencies ... done
Getting requirements to build wheel ... done
Installing backend dependencies ... done
Preparing metadata (pyproject.toml) ... done
Collecting boto3 (from suno-bark==0.0.1a0)
Downloading boto3-1.34.122-py3-none-any.whl (139 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 139.3/139.3 kB 3.6 MB/s eta 0:00:00
Collecting encodec (from suno-bark==0.0.1a0)
Downloading encodec-0.1.1.tar.gz (3.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.7/3.7 MB 49.7 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Collecting funcy (from suno-bark==0.0.1a0)
Downloading funcy-2.0-py2.py3-none-any.whl (30 kB)
Requirement already satisfied: huggingface-hub>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (0.23.2)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (1.25.2)
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (1.11.4)
Requirement already satisfied: tokenizers in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (0.19.1)
Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (2.3.0+cu121)
Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (4.66.4)
Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (from suno-bark==0.0.1a0) (4.41.2)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (3.14.0)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (2023.6.0)
Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (24.0)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (6.0.1)
Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (2.31.0)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (4.12.1)
Collecting botocore<1.35.0,>=1.34.122 (from boto3->suno-bark==0.0.1a0)
Downloading botocore-1.34.122-py3-none-any.whl (12.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.3/12.3 MB 77.9 MB/s eta 0:00:00
Collecting jmespath<2.0.0,>=0.7.1 (from boto3->suno-bark==0.0.1a0)
Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)
Collecting s3transfer<0.11.0,>=0.10.0 (from boto3->suno-bark==0.0.1a0)
Downloading s3transfer-0.10.1-py3-none-any.whl (82 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 82.2/82.2 kB 12.9 MB/s eta 0:00:00
Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (from encodec->suno-bark==0.0.1a0) (2.3.0+cu121)
Collecting einops (from encodec->suno-bark==0.0.1a0)
Downloading einops-0.8.0-py3-none-any.whl (43 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 43.2/43.2 kB 6.8 MB/s eta 0:00:00
Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->suno-bark==0.0.1a0) (1.12.1)
Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->suno-bark==0.0.1a0) (3.3)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->suno-bark==0.0.1a0) (3.1.4)
Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)
Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)
Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)
Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)
Collecting nvidia-cublas-cu12==12.1.3.1 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)
Collecting nvidia-cufft-cu12==11.0.2.54 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)
Collecting nvidia-curand-cu12==10.3.2.106 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)
Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)
Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)
Collecting nvidia-nccl-cu12==2.20.5 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)
Collecting nvidia-nvtx-cu12==12.1.105 (from torch->suno-bark==0.0.1a0)
Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)
Requirement already satisfied: triton==2.3.0 in /usr/local/lib/python3.10/dist-packages (from torch->suno-bark==0.0.1a0) (2.3.0)
Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch->suno-bark==0.0.1a0)
Downloading nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_x86_64.whl (21.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 21.3/21.3 MB 44.3 MB/s eta 0:00:00
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers->suno-bark==0.0.1a0) (2024.5.15)
Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers->suno-bark==0.0.1a0) (0.4.3)
Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /usr/local/lib/python3.10/dist-packages (from botocore<1.35.0,>=1.34.122->boto3->suno-bark==0.0.1a0) (2.8.2)
Requirement already satisfied: urllib3!=2.2.0,<3,>=1.25.4 in /usr/local/lib/python3.10/dist-packages (from botocore<1.35.0,>=1.34.122->boto3->suno-bark==0.0.1a0) (2.0.7)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->suno-bark==0.0.1a0) (2.1.5)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (3.7)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.14.1->suno-bark==0.0.1a0) (2024.6.2)
Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->suno-bark==0.0.1a0) (1.3.0)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil<3.0.0,>=2.1->botocore<1.35.0,>=1.34.122->boto3->suno-bark==0.0.1a0) (1.16.0)
Building wheels for collected packages: suno-bark, encodec
Building wheel for suno-bark (pyproject.toml) ... done
Created wheel for suno-bark: filename=suno_bark-0.0.1a0-py3-none-any.whl size=2567358 sha256=2270d76114b325bf7309b76a7e064066121456742c401d877d847eaa4999b507
Stored in directory: /tmp/pip-ephem-wheel-cache-l6h9fkbb/wheels/e6/6d/c2/107ed849afe600f905bb4049a026df3c7c5aa75d86c2721ec7
Building wheel for encodec (setup.py) ... done
Created wheel for encodec: filename=encodec-0.1.1-py3-none-any.whl size=45762 sha256=8664c39d36e420a024f02bd4af61fdcb6308e6786919f7c9277bdd52f006ba3f
Stored in directory: /root/.cache/pip/wheels/fc/36/cb/81af8b985a5f5e0815312d5e52b41263237af07b977e6bcbf3
Successfully built suno-bark encodec
Installing collected packages: funcy, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, jmespath, einops, nvidia-cusparse-cu12, nvidia-cudnn-cu12, botocore, s3transfer, nvidia-cusolver-cu12, boto3, encodec, suno-bark
Successfully installed boto3-1.34.122 botocore-1.34.122 einops-0.8.0 encodec-0.1.1 funcy-2.0 jmespath-1.0.1 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.5.40 nvidia-nvtx-cu12-12.1.105 s3transfer-0.10.1 suno-bark-0.0.1a0
Basics¶
In [2]:
from bark import SAMPLE_RATE, generate_audio, preload_models
from IPython.display import Audio
preload_models()
/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: The secret `HF_TOKEN` does not exist in your Colab secrets. To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session. You will be able to reuse this secret in all of your notebooks. Please note that authentication is recommended but still optional to access public models or datasets. warnings.warn(
text_2.pt: 0%| | 0.00/5.35G [00:00<?, ?B/s]
tokenizer_config.json: 0%| | 0.00/49.0 [00:00<?, ?B/s]
vocab.txt: 0%| | 0.00/996k [00:00<?, ?B/s]
tokenizer.json: 0%| | 0.00/1.96M [00:00<?, ?B/s]
/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. warnings.warn(
config.json: 0%| | 0.00/625 [00:00<?, ?B/s]
coarse_2.pt: 0%| | 0.00/3.93G [00:00<?, ?B/s]
fine_2.pt: 0%| | 0.00/3.74G [00:00<?, ?B/s]
/usr/local/lib/python3.10/dist-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Downloading: "https://dl.fbaipublicfiles.com/encodec/v0/encodec_24khz-d7cc33bc.th" to /root/.cache/torch/hub/checkpoints/encodec_24khz-d7cc33bc.th
100%|██████████| 88.9M/88.9M [00:01<00:00, 61.6MB/s]
In [22]:
# 0 : 기본 여성 목소리
# 6 : 중후한 교수님
# 7 : 걸걸한 교수님
# 8 : 나이 많으신 교수님
# 9 : 스프치 강사
number = 7 # 0 ~ 9
text_prompt = """
여러분의 제품에 API를 연동해 보고 싶으신가요?
"""
# text_prompt = "250쿼리를 제공 합니다." # Good : 1, 4
# https://github.com/suno-ai/bark/issues/380#issuecomment-1625127198
audio_array = generate_audio(text_prompt, history_prompt=f"v2/ko_speaker_{number}")
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 227/227 [00:03<00:00, 66.00it/s] 100%|██████████| 12/12 [00:16<00:00, 1.36s/it]
Out[22]:
In [25]:
number = 0 # 0 ~ 9
text_prompt = """
여러분의 제품에 API를 연동해 보고 싶으신가요?
"""
# text_prompt = "250쿼리를 제공 합니다." # Good : 1, 4
# https://github.com/suno-ai/bark/issues/380#issuecomment-1625127198
audio_array = generate_audio(text_prompt, history_prompt=f"v2/ko_speaker_{number}")
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 212/212 [00:03<00:00, 58.62it/s] 100%|██████████| 11/11 [00:11<00:00, 1.04s/it]
Out[25]:
In [24]:
number = 9 # 0 ~ 9
text_prompt = """
여러분의 제품에 API를 연동해 보고 싶으신가요?
"""
# text_prompt = "250쿼리를 제공 합니다." # Good : 1, 4
# https://github.com/suno-ai/bark/issues/380#issuecomment-1625127198
audio_array = generate_audio(text_prompt, history_prompt=f"v2/ko_speaker_{number}")
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 208/208 [00:03<00:00, 67.32it/s] 100%|██████████| 11/11 [00:15<00:00, 1.39s/it]
Out[24]:
In [ ]:
text_prompt = """
Hello, my name is Suno. And, uh — and I like pizza. [laughs]
But I also have other interests such as playing tic tac toe.
"""
audio_array = generate_audio(text_prompt)
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 100/100 [00:52<00:00, 1.91it/s] 100%|██████████| 26/26 [03:53<00:00, 8.98s/it]
Out[ ]:
Advanced examples¶
In [ ]:
text_prompt = """
Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo.
But I suppose your english isn't terrible.
"""
audio_array = generate_audio(text_prompt)
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 100/100 [01:01<00:00, 1.63it/s] 100%|██████████| 29/29 [04:41<00:00, 9.71s/it]
Out[ ]:
In [ ]:
text_prompt = """
WOMAN: I would like an oatmilk latte please.
MAN: Wow, that's expensive!
"""
audio_array = generate_audio(text_prompt)
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 100/100 [00:31<00:00, 3.20it/s] 100%|██████████| 17/17 [02:29<00:00, 8.82s/it]
Out[ ]:
In [ ]:
text_prompt = """
I have a silky smooth voice, and today I will tell you
about the exercise regimen of the common sloth.
"""
audio_array = generate_audio(text_prompt, history_prompt="v2/en_speaker_1")
Audio(audio_array, rate=SAMPLE_RATE)
100%|██████████| 100/100 [00:30<00:00, 3.23it/s] 100%|██████████| 19/19 [03:29<00:00, 11.05s/it]
Out[ ]:
In [ ]:
In [ ]: