Mirrors/bark-with-voice-clone
1
0
Fork 0
mirror of https://github.com/serp-ai/bark-with-voice-clone.git synced 2025-12-16 11:48:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

QoL updates

Browse Source
This commit is contained in:
Francis LaBounty
2023-04-22 16:47:01 -06:00
parent c9361469e3
commit 77f5f52136
2 changed files with 15 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
clone_voice.ipynb
View File

@@ -9,13 +9,10 @@
"from bark.generation import load_codec_model, generate_text_semantic\n", "from bark.generation import load_codec_model, generate_text_semantic\n",
"from encodec.utils import convert_audio\n", "from encodec.utils import convert_audio\n",
"\n", "\n",
"from transformers import BertTokenizer\n",
"\n",
"import torchaudio\n", "import torchaudio\n",
"import torch\n", "import torch\n",
"\n", "\n",
"model = load_codec_model(use_gpu=True)\n", "model = load_codec_model(use_gpu=True)"
"tokenizer = BertTokenizer.from_pretrained(\"bert-base-multilingual-cased\")"
] ]
}, },
{ {
@@ -119,9 +116,15 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"from bark.api import generate_audio\n", "from bark.api import generate_audio\n",
"from transformers import BertTokenizer\n",
"from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n", "from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"\n",
"# Enter your prompt and speaker here\n",
"text_prompt = \"Hello, my name is Serpy. And, uh — and I like pizza. [laughs]\"\n", "text_prompt = \"Hello, my name is Serpy. And, uh — and I like pizza. [laughs]\"\n",
"voice_name = \"speaker_0\" # use your custom voice name here if you have one" "voice_name = \"speaker_0\" # use your custom voice name here if you have one\n",
"\n",
"# load the tokenizer\n",
"tokenizer = BertTokenizer.from_pretrained(\"bert-base-multilingual-cased\")"
] ]
}, },
{ {

8
generate.ipynb
View File

@@ -7,9 +7,15 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"from bark.api import generate_audio\n", "from bark.api import generate_audio\n",
"from transformers import BertTokenizer\n",
"from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n", "from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"\n",
"# Enter your prompt and speaker here\n",
"text_prompt = \"Hello, my name is Serpy. And, uh — and I like pizza. [laughs]\"\n", "text_prompt = \"Hello, my name is Serpy. And, uh — and I like pizza. [laughs]\"\n",
"voice_name = \"speaker_0\" # use your custom voice name here if you have one" "voice_name = \"speaker_0\" # use your custom voice name here if you have one\n",
"\n",
"# load the tokenizer\n",
"tokenizer = BertTokenizer.from_pretrained(\"bert-base-multilingual-cased\")"
] ]
}, },
{ {