SOTA Open Source TTS
[pre-commit.ci] pre-commit autoupdate (#159)
pre-commit-ci[bot]40d8200c2d94
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yamlindex 71861cf..94969e0 100644--- a/.pre-commit-config.yaml+++ b/.pre-commit-config.yaml@@ -9,7 +9,7 @@ repos:args: [--profile=black]- repo: https://github.com/psf/black- rev: 23.12.1+ rev: 24.4.2hooks:- id: black@@ -21,7 +21,7 @@ repos:args: [-L=fro]- repo: https://github.com/pre-commit/pre-commit-hooks- rev: v4.5.0+ rev: v4.6.0hooks:- id: end-of-file-fixer- id: check-yamldiff --git a/fish_speech/utils/rich_utils.py b/fish_speech/utils/rich_utils.pyindex c8f77c7..6a465f5 100644--- a/fish_speech/utils/rich_utils.py+++ b/fish_speech/utils/rich_utils.py@@ -43,9 +43,13 @@ def print_config_tree(# add fields from `print_order` to queuefor field in print_order:- queue.append(field) if field in cfg else log.warning(- f"Field '{field}' not found in config. "- + f"Skipping '{field}' config printing..."+ (+ queue.append(field)+ if field in cfg+ else log.warning(+ f"Field '{field}' not found in config. "+ + f"Skipping '{field}' config printing..."+ ))# add all the other fields to queue (not specified in `print_order`)diff --git a/fish_speech/webui/launch_utils.py b/fish_speech/webui/launch_utils.pyindex a15091c..2f57b59 100644--- a/fish_speech/webui/launch_utils.py+++ b/fish_speech/webui/launch_utils.py@@ -83,16 +83,12 @@ class Seafoam(Base):spacing_size: sizes.Size | str = sizes.spacing_md,radius_size: sizes.Size | str = sizes.radius_md,text_size: sizes.Size | str = sizes.text_lg,- font: fonts.Font- | str- | Iterable[fonts.Font | str] = (+ font: fonts.Font | str | Iterable[fonts.Font | str] = (fonts.GoogleFont("Quicksand"),"ui-sans-serif","sans-serif",),- font_mono: fonts.Font- | str- | Iterable[fonts.Font | str] = (+ font_mono: fonts.Font | str | Iterable[fonts.Font | str] = (fonts.GoogleFont("IBM Plex Mono"),"ui-monospace","monospace",diff --git a/fish_speech/webui/manage.py b/fish_speech/webui/manage.pyindex 9c91a59..e86a3b8 100644--- a/fish_speech/webui/manage.py+++ b/fish_speech/webui/manage.py@@ -452,9 +452,7 @@ def train_process(project = (("vqgan_" + new_project)if vqgan_ckpt == "new"- else latest- if vqgan_ckpt == "latest"- else vqgan_ckpt+ else latest if vqgan_ckpt == "latest" else vqgan_ckpt)logger.info(project)train_cmd = [@@ -524,9 +522,7 @@ def train_process(project = (("text2semantic_" + new_project)if llama_ckpt == "new"- else latest- if llama_ckpt == "latest"- else llama_ckpt+ else latest if llama_ckpt == "latest" else llama_ckpt)logger.info(project)train_cmd = [@@ -861,9 +857,11 @@ with gr.Blocks(minimum=0,maximum=16,step=1,- value=init_llama_yml["data"]["num_workers"]- if sys.platform == "linux"- else 0,+ value=(+ init_llama_yml["data"]["num_workers"]+ if sys.platform == "linux"+ else 0+ ),)with gr.Row(equal_height=False):llama_data_batch_size_slider = gr.Slider(diff --git a/tools/whisper_asr.py b/tools/whisper_asr.pyindex d303607..5495953 100644--- a/tools/whisper_asr.py+++ b/tools/whisper_asr.py@@ -21,6 +21,7 @@ to transcribe the second speaker.Note: Be aware of your audio sample rate, which defaults to 44.1kHz."""+from pathlib import Pathimport click