SOTA Open Source TTS
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot]e2642d600730
diff --git a/fish_speech/text/clean.py b/fish_speech/text/clean.pyindex fe1b331..68428c4 100644--- a/fish_speech/text/clean.py+++ b/fish_speech/text/clean.py@@ -12,10 +12,10 @@ REPLACE_SYMBOL_REGEX = re.compile(EMOJI_REGEX = re.compile("["- "\U0001F600-\U0001F64F" # emoticons- "\U0001F300-\U0001F5FF" # symbols & pictographs- "\U0001F680-\U0001F6FF" # transport & map symbols- "\U0001F1E0-\U0001F1FF" # flags (iOS)+ "\U0001f600-\U0001f64f" # emoticons+ "\U0001f300-\U0001f5ff" # symbols & pictographs+ "\U0001f680-\U0001f6ff" # transport & map symbols+ "\U0001f1e0-\U0001f1ff" # flags (iOS)"]+",flags=re.UNICODE,)diff --git a/tools/webui/__init__.py b/tools/webui/__init__.pyindex 5e1301a..a31514e 100644--- a/tools/webui/__init__.py+++ b/tools/webui/__init__.py@@ -143,7 +143,7 @@ def build_app(inference_fct: Callable, theme: str = "light") -> gr.Blocks:with gr.Row():with gr.Column(scale=3):generate = gr.Button(- value="\U0001F3A7 " + i18n("Generate"),+ value="\U0001f3a7 " + i18n("Generate"),variant="primary",)diff --git a/tools/whisper_asr.py b/tools/whisper_asr.pyindex 6494e62..1c34efb 100644--- a/tools/whisper_asr.py+++ b/tools/whisper_asr.py@@ -11,12 +11,12 @@ Directory structure:------01.wav------02.wav------......-Use-python tools/whisper_asr.py --audio-dir pre_data_root/SP_1 --save-dir data/SP_1+Use+python tools/whisper_asr.py --audio-dir pre_data_root/SP_1 --save-dir data/SP_1to transcribe the first speaker.-Use-python tools/whisper_asr.py --audio-dir pre_data_root/SP_2 --save-dir data/SP_2+Use+python tools/whisper_asr.py --audio-dir pre_data_root/SP_2 --save-dir data/SP_2to transcribe the second speaker.Note: Be aware of your audio sample rate, which defaults to 44.1kHz.