{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "07a3dd21" }, "source": [ "### Install Chatterbox-TTS Library" ], "id": "07a3dd21" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "ereyVE-BNScG", "outputId": "8ee6189e-e970-4854-e505-9dfb5cba4025", "collapsed": true }, "source": [ "!pip install chatterbox-tts==0.1.1" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting chatterbox-tts==0.1.1\n", " Downloading chatterbox_tts-0.1.1-py3-none-any.whl.metadata (5.9 kB)\n", "Collecting numpy==1.26.0 (from chatterbox-tts==0.1.1)\n", " Downloading numpy-1.26.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (58 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.5/58.5 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting resampy==0.4.3 (from chatterbox-tts==0.1.1)\n", " Downloading resampy-0.4.3-py3-none-any.whl.metadata (3.0 kB)\n", "Collecting librosa==0.10.0 (from chatterbox-tts==0.1.1)\n", " Downloading librosa-0.10.0-py3-none-any.whl.metadata (8.3 kB)\n", "Collecting s3tokenizer (from chatterbox-tts==0.1.1)\n", " Downloading s3tokenizer-0.2.0.tar.gz (225 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.2/225.2 kB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Collecting torch==2.6.0 (from chatterbox-tts==0.1.1)\n", " Downloading torch-2.6.0-cp312-cp312-manylinux1_x86_64.whl.metadata (28 kB)\n", "Collecting torchaudio==2.6.0 (from chatterbox-tts==0.1.1)\n", " Downloading torchaudio-2.6.0-cp312-cp312-manylinux1_x86_64.whl.metadata (6.6 kB)\n", "Collecting transformers==4.46.3 (from chatterbox-tts==0.1.1)\n", " Downloading transformers-4.46.3-py3-none-any.whl.metadata (44 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.1/44.1 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting diffusers==0.29.0 (from chatterbox-tts==0.1.1)\n", " Downloading diffusers-0.29.0-py3-none-any.whl.metadata (19 kB)\n", "Collecting resemble-perth==1.0.1 (from chatterbox-tts==0.1.1)\n", " Downloading resemble_perth-1.0.1-py3-none-any.whl.metadata (4.8 kB)\n", "Requirement already satisfied: omegaconf==2.3.0 in /usr/local/lib/python3.12/dist-packages (from chatterbox-tts==0.1.1) (2.3.0)\n", "Collecting conformer==0.3.2 (from chatterbox-tts==0.1.1)\n", " Downloading conformer-0.3.2-py3-none-any.whl.metadata (631 bytes)\n", "Requirement already satisfied: einops>=0.6.1 in /usr/local/lib/python3.12/dist-packages (from conformer==0.3.2->chatterbox-tts==0.1.1) (0.8.1)\n", "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (8.7.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (3.19.1)\n", "Requirement already satisfied: huggingface-hub>=0.23.2 in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (0.34.4)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (2024.11.6)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (2.32.4)\n", "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (0.6.2)\n", "Requirement already satisfied: Pillow in /usr/local/lib/python3.12/dist-packages (from diffusers==0.29.0->chatterbox-tts==0.1.1) (11.3.0)\n", "Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (3.0.1)\n", "Requirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (1.16.1)\n", "Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (1.6.1)\n", "Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (1.5.2)\n", "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (4.4.2)\n", "Requirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (0.60.0)\n", "Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (0.13.1)\n", "Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (1.8.2)\n", "Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (0.5.0.post1)\n", "Requirement already satisfied: typing-extensions>=4.1.1 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (4.15.0)\n", "Requirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (0.4)\n", "Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.12/dist-packages (from librosa==0.10.0->chatterbox-tts==0.1.1) (1.1.1)\n", "Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.12/dist-packages (from omegaconf==2.3.0->chatterbox-tts==0.1.1) (4.9.3)\n", "Requirement already satisfied: PyYAML>=5.1.0 in /usr/local/lib/python3.12/dist-packages (from omegaconf==2.3.0->chatterbox-tts==0.1.1) (6.0.2)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch==2.6.0->chatterbox-tts==0.1.1) (3.5)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch==2.6.0->chatterbox-tts==0.1.1) (3.1.6)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch==2.6.0->chatterbox-tts==0.1.1) (2025.3.0)\n", "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-curand-cu12==10.3.5.147 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cusparselt-cu12==0.6.2 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl.metadata (6.8 kB)\n", "Collecting nvidia-nccl-cu12==2.21.5 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n", "Collecting nvidia-nvtx-cu12==12.4.127 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.7 kB)\n", "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Collecting triton==3.2.0 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch==2.6.0->chatterbox-tts==0.1.1) (75.2.0)\n", "Collecting sympy==1.13.1 (from torch==2.6.0->chatterbox-tts==0.1.1)\n", " Downloading sympy-1.13.1-py3-none-any.whl.metadata (12 kB)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers==4.46.3->chatterbox-tts==0.1.1) (25.0)\n", "Collecting tokenizers<0.21,>=0.20 (from transformers==4.46.3->chatterbox-tts==0.1.1)\n", " Downloading tokenizers-0.20.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n", "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers==4.46.3->chatterbox-tts==0.1.1) (4.67.1)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy==1.13.1->torch==2.6.0->chatterbox-tts==0.1.1) (1.3.0)\n", "Collecting pre-commit (from s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading pre_commit-4.3.0-py2.py3-none-any.whl.metadata (1.2 kB)\n", "Collecting onnx (from s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading onnx-1.19.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (7.0 kB)\n", "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.23.2->diffusers==0.29.0->chatterbox-tts==0.1.1) (1.1.9)\n", "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.51.0->librosa==0.10.0->chatterbox-tts==0.1.1) (0.43.0)\n", "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from pooch>=1.0->librosa==0.10.0->chatterbox-tts==0.1.1) (4.4.0)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.29.0->chatterbox-tts==0.1.1) (3.4.3)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.29.0->chatterbox-tts==0.1.1) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.29.0->chatterbox-tts==0.1.1) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.29.0->chatterbox-tts==0.1.1) (2025.8.3)\n", "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=0.20.0->librosa==0.10.0->chatterbox-tts==0.1.1) (3.6.0)\n", "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.12/dist-packages (from soundfile>=0.12.1->librosa==0.10.0->chatterbox-tts==0.1.1) (1.17.1)\n", "Requirement already satisfied: zipp>=3.20 in /usr/local/lib/python3.12/dist-packages (from importlib-metadata->diffusers==0.29.0->chatterbox-tts==0.1.1) (3.23.0)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch==2.6.0->chatterbox-tts==0.1.1) (3.0.2)\n", "Requirement already satisfied: protobuf>=4.25.1 in /usr/local/lib/python3.12/dist-packages (from onnx->s3tokenizer->chatterbox-tts==0.1.1) (5.29.5)\n", "Requirement already satisfied: ml_dtypes in /usr/local/lib/python3.12/dist-packages (from onnx->s3tokenizer->chatterbox-tts==0.1.1) (0.5.3)\n", "Collecting cfgv>=2.0.0 (from pre-commit->s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading cfgv-3.4.0-py2.py3-none-any.whl.metadata (8.5 kB)\n", "Collecting identify>=1.0.0 (from pre-commit->s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading identify-2.6.14-py2.py3-none-any.whl.metadata (4.4 kB)\n", "Collecting nodeenv>=0.11.1 (from pre-commit->s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading nodeenv-1.9.1-py2.py3-none-any.whl.metadata (21 kB)\n", "Collecting virtualenv>=20.10.0 (from pre-commit->s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading virtualenv-20.34.0-py3-none-any.whl.metadata (4.6 kB)\n", "Requirement already satisfied: pycparser in /usr/local/lib/python3.12/dist-packages (from cffi>=1.0->soundfile>=0.12.1->librosa==0.10.0->chatterbox-tts==0.1.1) (2.22)\n", "Collecting distlib<1,>=0.3.7 (from virtualenv>=20.10.0->pre-commit->s3tokenizer->chatterbox-tts==0.1.1)\n", " Downloading distlib-0.4.0-py2.py3-none-any.whl.metadata (5.2 kB)\n", "Downloading chatterbox_tts-0.1.1-py3-none-any.whl (91 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.4/91.4 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading conformer-0.3.2-py3-none-any.whl (4.3 kB)\n", "Downloading diffusers-0.29.0-py3-none-any.whl (2.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m58.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading librosa-0.10.0-py3-none-any.whl (252 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m252.9/252.9 kB\u001b[0m \u001b[31m25.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading numpy-1.26.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.9/17.9 MB\u001b[0m \u001b[31m58.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading resampy-0.4.3-py3-none-any.whl (3.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m83.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading resemble_perth-1.0.1-py3-none-any.whl (34.4 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m34.4/34.4 MB\u001b[0m \u001b[31m15.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading torch-2.6.0-cp312-cp312-manylinux1_x86_64.whl (766.6 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m766.6/766.6 MB\u001b[0m \u001b[31m1.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading torchaudio-2.6.0-cp312-cp312-manylinux1_x86_64.whl (3.4 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m57.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading transformers-4.46.3-py3-none-any.whl (10.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.0/10.0 MB\u001b[0m \u001b[31m65.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m84.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m59.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m51.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m15.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl (150.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m150.1/150.1 MB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl (188.7 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m188.7/188.7 MB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m59.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (99 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading sympy-1.13.1-py3-none-any.whl (6.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.2/6.2 MB\u001b[0m \u001b[31m50.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (253.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m253.2/253.2 MB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading tokenizers-0.20.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m76.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading onnx-1.19.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (18.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m24.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading pre_commit-4.3.0-py2.py3-none-any.whl (220 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m221.0/221.0 kB\u001b[0m \u001b[31m25.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading cfgv-3.4.0-py2.py3-none-any.whl (7.2 kB)\n", "Downloading identify-2.6.14-py2.py3-none-any.whl (99 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.2/99.2 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading nodeenv-1.9.1-py2.py3-none-any.whl (22 kB)\n", "Downloading virtualenv-20.34.0-py3-none-any.whl (6.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.0/6.0 MB\u001b[0m \u001b[31m74.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading distlib-0.4.0-py2.py3-none-any.whl (469 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m469.0/469.0 kB\u001b[0m \u001b[31m42.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hBuilding wheels for collected packages: s3tokenizer\n", " Building wheel for s3tokenizer (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for s3tokenizer: filename=s3tokenizer-0.2.0-py3-none-any.whl size=221564 sha256=c2ba19abe25d852732425c9a94958d648a0d1f83f65cc76bd0c905093e22c607\n", " Stored in directory: /root/.cache/pip/wheels/bb/b7/c0/8cbcc805e7cc360cf38296016fb2dd0324cc7b3fb90e3baf7a\n", "Successfully built s3tokenizer\n", "Installing collected packages: triton, nvidia-cusparselt-cu12, distlib, virtualenv, sympy, resemble-perth, 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, numpy, nodeenv, identify, cfgv, pre-commit, nvidia-cusparse-cu12, nvidia-cudnn-cu12, tokenizers, resampy, onnx, nvidia-cusolver-cu12, diffusers, transformers, torch, librosa, torchaudio, conformer, s3tokenizer, chatterbox-tts\n", " Attempting uninstall: triton\n", " Found existing installation: triton 3.4.0\n", " Uninstalling triton-3.4.0:\n", " Successfully uninstalled triton-3.4.0\n", " Attempting uninstall: nvidia-cusparselt-cu12\n", " Found existing installation: nvidia-cusparselt-cu12 0.7.1\n", " Uninstalling nvidia-cusparselt-cu12-0.7.1:\n", " Successfully uninstalled nvidia-cusparselt-cu12-0.7.1\n", " Attempting uninstall: sympy\n", " Found existing installation: sympy 1.13.3\n", " Uninstalling sympy-1.13.3:\n", " Successfully uninstalled sympy-1.13.3\n", " Attempting uninstall: nvidia-nvtx-cu12\n", " Found existing installation: nvidia-nvtx-cu12 12.6.77\n", " Uninstalling nvidia-nvtx-cu12-12.6.77:\n", " Successfully uninstalled nvidia-nvtx-cu12-12.6.77\n", " Attempting uninstall: nvidia-nvjitlink-cu12\n", " Found existing installation: nvidia-nvjitlink-cu12 12.6.85\n", " Uninstalling nvidia-nvjitlink-cu12-12.6.85:\n", " Successfully uninstalled nvidia-nvjitlink-cu12-12.6.85\n", " Attempting uninstall: nvidia-nccl-cu12\n", " Found existing installation: nvidia-nccl-cu12 2.27.3\n", " Uninstalling nvidia-nccl-cu12-2.27.3:\n", " Successfully uninstalled nvidia-nccl-cu12-2.27.3\n", " Attempting uninstall: nvidia-curand-cu12\n", " Found existing installation: nvidia-curand-cu12 10.3.7.77\n", " Uninstalling nvidia-curand-cu12-10.3.7.77:\n", " Successfully uninstalled nvidia-curand-cu12-10.3.7.77\n", " Attempting uninstall: nvidia-cufft-cu12\n", " Found existing installation: nvidia-cufft-cu12 11.3.0.4\n", " Uninstalling nvidia-cufft-cu12-11.3.0.4:\n", " Successfully uninstalled nvidia-cufft-cu12-11.3.0.4\n", " Attempting uninstall: nvidia-cuda-runtime-cu12\n", " Found existing installation: nvidia-cuda-runtime-cu12 12.6.77\n", " Uninstalling nvidia-cuda-runtime-cu12-12.6.77:\n", " Successfully uninstalled nvidia-cuda-runtime-cu12-12.6.77\n", " Attempting uninstall: nvidia-cuda-nvrtc-cu12\n", " Found existing installation: nvidia-cuda-nvrtc-cu12 12.6.77\n", " Uninstalling nvidia-cuda-nvrtc-cu12-12.6.77:\n", " Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.6.77\n", " Attempting uninstall: nvidia-cuda-cupti-cu12\n", " Found existing installation: nvidia-cuda-cupti-cu12 12.6.80\n", " Uninstalling nvidia-cuda-cupti-cu12-12.6.80:\n", " Successfully uninstalled nvidia-cuda-cupti-cu12-12.6.80\n", " Attempting uninstall: nvidia-cublas-cu12\n", " Found existing installation: nvidia-cublas-cu12 12.6.4.1\n", " Uninstalling nvidia-cublas-cu12-12.6.4.1:\n", " Successfully uninstalled nvidia-cublas-cu12-12.6.4.1\n", " Attempting uninstall: numpy\n", " Found existing installation: numpy 2.0.2\n", " Uninstalling numpy-2.0.2:\n", " Successfully uninstalled numpy-2.0.2\n", " Attempting uninstall: nvidia-cusparse-cu12\n", " Found existing installation: nvidia-cusparse-cu12 12.5.4.2\n", " Uninstalling nvidia-cusparse-cu12-12.5.4.2:\n", " Successfully uninstalled nvidia-cusparse-cu12-12.5.4.2\n", " Attempting uninstall: nvidia-cudnn-cu12\n", " Found existing installation: nvidia-cudnn-cu12 9.10.2.21\n", " Uninstalling nvidia-cudnn-cu12-9.10.2.21:\n", " Successfully uninstalled nvidia-cudnn-cu12-9.10.2.21\n", " Attempting uninstall: tokenizers\n", " Found existing installation: tokenizers 0.22.0\n", " Uninstalling tokenizers-0.22.0:\n", " Successfully uninstalled tokenizers-0.22.0\n", " Attempting uninstall: nvidia-cusolver-cu12\n", " Found existing installation: nvidia-cusolver-cu12 11.7.1.2\n", " Uninstalling nvidia-cusolver-cu12-11.7.1.2:\n", " Successfully uninstalled nvidia-cusolver-cu12-11.7.1.2\n", " Attempting uninstall: diffusers\n", " Found existing installation: diffusers 0.35.1\n", " Uninstalling diffusers-0.35.1:\n", " Successfully uninstalled diffusers-0.35.1\n", " Attempting uninstall: transformers\n", " Found existing installation: transformers 4.56.1\n", " Uninstalling transformers-4.56.1:\n", " Successfully uninstalled transformers-4.56.1\n", " Attempting uninstall: torch\n", " Found existing installation: torch 2.8.0+cu126\n", " Uninstalling torch-2.8.0+cu126:\n", " Successfully uninstalled torch-2.8.0+cu126\n", " Attempting uninstall: librosa\n", " Found existing installation: librosa 0.11.0\n", " Uninstalling librosa-0.11.0:\n", " Successfully uninstalled librosa-0.11.0\n", " Attempting uninstall: torchaudio\n", " Found existing installation: torchaudio 2.8.0+cu126\n", " Uninstalling torchaudio-2.8.0+cu126:\n", " Successfully uninstalled torchaudio-2.8.0+cu126\n", "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "opencv-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.0 which is incompatible.\n", "thinc 8.3.6 requires numpy<3.0.0,>=2.0.0, but you have numpy 1.26.0 which is incompatible.\n", "torchvision 0.23.0+cu126 requires torch==2.8.0, but you have torch 2.6.0 which is incompatible.\n", "opencv-python-headless 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.0 which is incompatible.\n", "opencv-contrib-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.0 which is incompatible.\u001b[0m\u001b[31m\n", "\u001b[0mSuccessfully installed cfgv-3.4.0 chatterbox-tts-0.1.1 conformer-0.3.2 diffusers-0.29.0 distlib-0.4.0 identify-2.6.14 librosa-0.10.0 nodeenv-1.9.1 numpy-1.26.0 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-cusparselt-cu12-0.6.2 nvidia-nccl-cu12-2.21.5 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.4.127 onnx-1.19.0 pre-commit-4.3.0 resampy-0.4.3 resemble-perth-1.0.1 s3tokenizer-0.2.0 sympy-1.13.1 tokenizers-0.20.3 torch-2.6.0 torchaudio-2.6.0 transformers-4.46.3 triton-3.2.0 virtualenv-20.34.0\n" ] }, { "output_type": "display_data", "data": { "application/vnd.colab-display-data+json": { "pip_warning": { "packages": [ "numpy" ] }, "id": "c974d6ced5b246b5907926ba390e4b09" } }, "metadata": {} } ], "id": "ereyVE-BNScG" }, { "cell_type": "markdown", "metadata": { "id": "22fb82f2" }, "source": [ "### Clone and Prepare Fine-tuning Repository" ], "id": "22fb82f2" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "DY57ULAnNScJ", "outputId": "668e8579-000a-4535-9698-a9ff3187054a", "collapsed": true }, "source": [ "!git clone https://github.com/stlohrey/chatterbox-finetuning.git\n", "%cd chatterbox-finetuning/src\n", "!huggingface-cli login --token " ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Cloning into 'chatterbox-finetuning'...\n", "remote: Enumerating objects: 175, done.\u001b[K\n", "remote: Counting objects: 100% (78/78), done.\u001b[K\n", "remote: Compressing objects: 100% (51/51), done.\u001b[K\n", "remote: Total 175 (delta 28), reused 27 (delta 27), pack-reused 97 (from 1)\u001b[K\n", "Receiving objects: 100% (175/175), 137.23 KiB | 7.62 MiB/s, done.\n", "Resolving deltas: 100% (62/62), done.\n", "/content/chatterbox-finetuning/src\n", "\u001b[33m⚠️ Warning: 'huggingface-cli login' is deprecated. Use 'hf auth login' instead.\u001b[0m\n", "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `hf`CLI if you want to set the git credential as well.\n", "Token is valid (permission: write).\n", "The token `Write` has been saved to /root/.cache/huggingface/stored_tokens\n", "Your token has been saved to /root/.cache/huggingface/token\n", "Login successful.\n", "The current active token is: `Write`\n" ] } ], "id": "DY57ULAnNScJ" }, { "cell_type": "markdown", "metadata": { "id": "c4d1354a" }, "source": [ "### Install Required Libraries" ], "id": "c4d1354a" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "A0wH3HCvNScK", "outputId": "57cc8ad6-4758-467c-e3ec-50f1cf8116ac", "collapsed": true }, "source": [ "!pip install transformers==4.44.2 peft==0.11.1\n", "!pip install -U ml_dtypes\n", "!pip install \"datasets>=3.4.1,<4.0.0\"" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting transformers==4.44.2\n", " Downloading transformers-4.44.2-py3-none-any.whl.metadata (43 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/43.7 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.7/43.7 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting peft==0.11.1\n", " Downloading peft-0.11.1-py3-none-any.whl.metadata (13 kB)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (3.19.1)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (0.34.4)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (1.26.0)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (25.0)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (6.0.2)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (2024.11.6)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (2.32.4)\n", "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (0.6.2)\n", "Collecting tokenizers<0.20,>=0.19 (from transformers==4.44.2)\n", " Downloading tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n", "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers==4.44.2) (4.67.1)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.12/dist-packages (from peft==0.11.1) (5.9.5)\n", "Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.12/dist-packages (from peft==0.11.1) (2.6.0)\n", "Requirement already satisfied: accelerate>=0.21.0 in /usr/local/lib/python3.12/dist-packages (from peft==0.11.1) (1.10.1)\n", "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.44.2) (2025.3.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.44.2) (4.15.0)\n", "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.44.2) (1.1.9)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (3.5)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (3.1.6)\n", "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.127)\n", "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.127)\n", "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.127)\n", "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (9.1.0.70)\n", "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.5.8)\n", "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (11.2.1.3)\n", "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (10.3.5.147)\n", "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (11.6.1.9)\n", "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.3.1.170)\n", "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (0.6.2)\n", "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (2.21.5)\n", "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.127)\n", "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (12.4.127)\n", "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (3.2.0)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (75.2.0)\n", "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->peft==0.11.1) (1.13.1)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy==1.13.1->torch>=1.13.0->peft==0.11.1) (1.3.0)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.44.2) (3.4.3)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.44.2) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.44.2) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.44.2) (2025.8.3)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.13.0->peft==0.11.1) (3.0.2)\n", "Downloading transformers-4.44.2-py3-none-any.whl (9.5 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.5/9.5 MB\u001b[0m \u001b[31m68.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading peft-0.11.1-py3-none-any.whl (251 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.6/251.6 kB\u001b[0m \u001b[31m14.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m28.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: tokenizers, transformers, peft\n", " Attempting uninstall: tokenizers\n", " Found existing installation: tokenizers 0.20.3\n", " Uninstalling tokenizers-0.20.3:\n", " Successfully uninstalled tokenizers-0.20.3\n", " Attempting uninstall: transformers\n", " Found existing installation: transformers 4.46.3\n", " Uninstalling transformers-4.46.3:\n", " Successfully uninstalled transformers-4.46.3\n", " Attempting uninstall: peft\n", " Found existing installation: peft 0.17.1\n", " Uninstalling peft-0.17.1:\n", " Successfully uninstalled peft-0.17.1\n", "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "chatterbox-tts 0.1.1 requires transformers==4.46.3, but you have transformers 4.44.2 which is incompatible.\u001b[0m\u001b[31m\n", "\u001b[0mSuccessfully installed peft-0.11.1 tokenizers-0.19.1 transformers-4.44.2\n", "Requirement already satisfied: ml_dtypes in /usr/local/lib/python3.12/dist-packages (0.5.3)\n", "Requirement already satisfied: numpy>=1.21 in /usr/local/lib/python3.12/dist-packages (from ml_dtypes) (1.26.0)\n", "Collecting datasets<4.0.0,>=3.4.1\n", " Downloading datasets-3.6.0-py3-none-any.whl.metadata (19 kB)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (3.19.1)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (1.26.0)\n", "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (18.1.0)\n", "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (0.3.8)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (2.2.2)\n", "Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (2.32.4)\n", "Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (4.67.1)\n", "Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (3.5.0)\n", "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (0.70.16)\n", "Requirement already satisfied: fsspec<=2025.3.0,>=2023.1.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (2025.3.0)\n", "Requirement already satisfied: huggingface-hub>=0.24.0 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (0.34.4)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (25.0)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets<4.0.0,>=3.4.1) (6.0.2)\n", "Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (3.12.15)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.24.0->datasets<4.0.0,>=3.4.1) (4.15.0)\n", "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.24.0->datasets<4.0.0,>=3.4.1) (1.1.9)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets<4.0.0,>=3.4.1) (3.4.3)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets<4.0.0,>=3.4.1) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets<4.0.0,>=3.4.1) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets<4.0.0,>=3.4.1) (2025.8.3)\n", "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets<4.0.0,>=3.4.1) (2.9.0.post0)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets<4.0.0,>=3.4.1) (2025.2)\n", "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets<4.0.0,>=3.4.1) (2025.2)\n", "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (2.6.1)\n", "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (1.4.0)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (25.3.0)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (1.7.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (6.6.4)\n", "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (0.3.2)\n", "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets<4.0.0,>=3.4.1) (1.20.1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->datasets<4.0.0,>=3.4.1) (1.17.0)\n", "Downloading datasets-3.6.0-py3-none-any.whl (491 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m491.5/491.5 kB\u001b[0m \u001b[31m31.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: datasets\n", " Attempting uninstall: datasets\n", " Found existing installation: datasets 4.0.0\n", " Uninstalling datasets-4.0.0:\n", " Successfully uninstalled datasets-4.0.0\n", "Successfully installed datasets-3.6.0\n" ] } ], "id": "A0wH3HCvNScK" }, { "cell_type": "markdown", "metadata": { "id": "3b8c7ce9" }, "source": [ "### Fine-tune the Chatterbox TTS Model" ], "id": "3b8c7ce9" }, { "cell_type": "code", "metadata": { "scrolled": true, "id": "BbZXPUiPNScL", "collapsed": true }, "source": [ "!python finetune_t3.py \\\n", " --output_dir ./checkpoints/chatterbox_finetuned \\\n", " --model_name_or_path ResembleAI/chatterbox \\\n", " --dataset_name \\\n", " --train_split_name train \\\n", " --eval_split_size 0.1 \\\n", " --num_train_epochs 8 \\\n", " --per_device_train_batch_size 4 \\\n", " --gradient_accumulation_steps 2 \\\n", " --learning_rate 1e-5 \\\n", " --warmup_steps 5 \\\n", " --logging_steps 20 \\\n", " --eval_strategy steps \\\n", " --eval_steps 60 \\\n", " --save_strategy steps \\\n", " --save_steps 90 \\\n", " --save_total_limit 2 \\\n", " --fp16 True \\\n", " --report_to tensorboard \\\n", " --dataloader_num_workers 2 \\\n", " --do_train \\\n", " --do_eval \\\n", " --dataloader_pin_memory False \\\n", " --eval_on_start True \\\n", " --label_names labels_speech \\\n", " --text_column_name text" ], "execution_count": null, "outputs": [], "id": "BbZXPUiPNScL" }, { "cell_type": "markdown", "metadata": { "id": "lCgLpsia953w" }, "source": [ "### Test Fine-tune the Chatterbox TTS Model" ], "id": "lCgLpsia953w" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "GCmoPSzINScL", "outputId": "51bea3f4-4cc0-450a-a881-18e7a63a890c", "collapsed": true }, "source": [ "# List the contents of the checkpoints directory\n", "ls ./checkpoints/chatterbox_finetuned" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "all_results.json model.safetensors tokenizer.json\n", "\u001b[0m\u001b[01;34mcheckpoint-400\u001b[0m/ \u001b[01;34mpretrained_model_download\u001b[0m/ trainer_state.json\n", "\u001b[01;34mcheckpoint-575\u001b[0m/ \u001b[01;34mruns\u001b[0m/ training_args.bin\n", "conds.pt s3gen.safetensors train_results.json\n", "eval_results.json t3_cfg.safetensors ve.safetensors\n" ] } ], "id": "GCmoPSzINScL" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/", "height": 234 }, "id": "77G5KuJYNScM", "outputId": "94ed83db-934c-407e-b09c-0b5c8d7359ad", "collapsed": true }, "source": [ "import torch\n", "import torchaudio as ta\n", "\n", "from chatterbox.tts import ChatterboxTTS\n", "from safetensors.torch import load_file\n", "from IPython.display import Audio\n", "from pathlib import Path\n", "\n", "# Specify the checkpoint directory\n", "ckpt_dir = Path(\"./checkpoints/chatterbox_finetuned\")\n", "\n", "# Load the ChatterboxTTS model from the local checkpoint directory\n", "model = ChatterboxTTS.from_local(ckpt_dir, device=\"cuda\")\n", "\n", "# Input text for synthesis\n", "text = \"Bahwa sesungguhnya kemerdekaan itu ialah hak segala bangsa dan oleh sebab itu, maka penjajahan di atas dunia harus dihapuskan, karena tidak sesuai dengan peri kemanusiaan dan peri-keadilan.\"\n", "\n", "# Generate waveform from the input text\n", "wav_audio = model.generate(text=text)\n", "\n", "# Play the generated audio in the notebook\n", "display(Audio(wav_audio.numpy(), rate=model.sr))" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.\n", " deprecate(\"LoRACompatibleLinear\", \"1.0.0\", deprecation_message)\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "loaded PerthNet (Implicit) at step 250,000\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/lib/python3.12/contextlib.py:105: FutureWarning: `torch.backends.cuda.sdp_kernel()` is deprecated. In the future, this context manager will be removed. Please see `torch.nn.attention.sdpa_kernel()` for the new context manager, with updated signature.\n", " self.gen = func(*args, **kwds)\n", "We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)\n", "LlamaModel is using LlamaSdpaAttention, but `torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to the manual attention implementation, but specifying the manual implementation will be required from Transformers version v5.0.0 onwards. This warning can be removed using the argument `attn_implementation=\"eager\"` when loading the model.\n", "Sampling: 26%|██▌ | 257/1000 [00:08<00:24, 29.94it/s]\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ], "id": "77G5KuJYNScM" }, { "cell_type": "code", "metadata": { "scrolled": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "tK_zgEtUNScM", "outputId": "4a45d40a-715f-47f0-ebfe-eaf6dfd10f71" }, "source": [ "# Print the current working directory\n", "!pwd" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "/content/chatterbox-finetuning/src\n" ] } ], "id": "tK_zgEtUNScM" }, { "cell_type": "code", "metadata": { "scrolled": true, "id": "LLCdAH_7NScN" }, "source": [ "from huggingface_hub import HfApi\n", "\n", "# Initialize HfApi with your token\n", "api = HfApi(token=\"\")\n", "# Upload the finetuned model to Hugging Face Hub\n", "api.upload_folder(\n", " folder_path=\"/root/chatterbox-finetuning/src/checkpoints/chatterbox_finetuned\",\n", " repo_id=\"\",\n", " repo_type=\"model\",\n", ")" ], "execution_count": null, "outputs": [], "id": "LLCdAH_7NScN" } ], "metadata": { "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3" }, "colab": { "provenance": [], "gpuType": "T4" }, "accelerator": "GPU" }, "nbformat": 4, "nbformat_minor": 5 }