Mirrors/bark-with-voice-clone
1
0
Fork 0
mirror of https://github.com/serp-ai/bark-with-voice-clone.git synced 2025-12-15 19:27:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

QoL updates

Browse Source
This commit is contained in:
Francis LaBounty
2023-04-22 16:43:14 -06:00
parent 282152ec28
commit 72f0afe683
2 changed files with 40 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
clone_voice.ipynb
View File

@@ -119,11 +119,30 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"from bark.api import generate_audio\n", "from bark.api import generate_audio\n",
"from bark.generation import SAMPLE_RATE\n", "from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"text_prompt = \"Hello, my name is Suno. And, uh — and I like pizza. [laughs]\"\n", "text_prompt = \"Hello, my name is Suno. 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"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# download and load all models\n",
"preload_models(\n",
" text_use_gpu=True,\n",
" text_use_small=False,\n",
" coarse_use_gpu=True,\n",
" coarse_use_small=False,\n",
" fine_use_gpu=True,\n",
" fine_use_small=False,\n",
" codec_use_gpu=True,\n",
" force_reload=False\n",
")"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
@@ -141,7 +160,6 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# generation with more control\n", "# generation with more control\n",
"from bark.generation import codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"x_semantic = generate_text_semantic(\n", "x_semantic = generate_text_semantic(\n",
" text_prompt,\n", " text_prompt,\n",
" history_prompt=voice_name,\n", " history_prompt=voice_name,\n",

22
generate.ipynb
View File

@@ -7,11 +7,30 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"from bark.api import generate_audio\n", "from bark.api import generate_audio\n",
"from bark.generation import SAMPLE_RATE\n", "from bark.generation import SAMPLE_RATE, preload_models, codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"text_prompt = \"Hello, my name is Suno. And, uh — and I like pizza. [laughs]\"\n", "text_prompt = \"Hello, my name is Suno. 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"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# download and load all models\n",
"preload_models(\n",
" text_use_gpu=True,\n",
" text_use_small=False,\n",
" coarse_use_gpu=True,\n",
" coarse_use_small=False,\n",
" fine_use_gpu=True,\n",
" fine_use_small=False,\n",
" codec_use_gpu=True,\n",
" force_reload=False\n",
")"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
@@ -29,7 +48,6 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"# generation with more control\n", "# generation with more control\n",
"from bark.generation import codec_decode, generate_coarse, generate_fine, generate_text_semantic\n",
"x_semantic = generate_text_semantic(\n", "x_semantic = generate_text_semantic(\n",
" text_prompt,\n", " text_prompt,\n",
" history_prompt=voice_name,\n", " history_prompt=voice_name,\n",