kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #14 from erew123/dev

Browse Source 
New Finetuning of your models
New API endpoint
Full documentation (online and built in)
A couple of minor file updates.
Small bug fix on file generation in instruct mode with no character name available (thanks to @danielwburch)
This commit is contained in:
erew123 authored and GitHub committed 2023-12-24 13:10:18 +00:00
2 parents b5b68ad51f bb81f3f874
commit f2119aa0f7
9 files changed
+1652 -51
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

script.py
+13 -20
View File
@@ -39,8 +39,8 @@ try:
except ModuleNotFoundError:
logger.error(
f"[{params['branding']}]\033[91mWarning\033[0m Could not find the TTS module. Make sure to install the requirements for the {params['branding']} extension."
f"[{params['branding']}]\033[91mWarning\033[0m Linux / Mac:\npip install -r extensions/alltalk_tts/requirements.txt\n"
f"[{params['branding']}]\033[91mWarning\033[0m Windows:\npip install -r extensions\\alltalk_tts\\requirements.txt\n"
f"[{params['branding']}]\033[91mWarning\033[0m Linux / Mac:\npip install -r /alltalk_tts/requirements.txt\n"
f"[{params['branding']}]\033[91mWarning\033[0m Windows:\npip install -r \\alltalk_tts\\requirements.txt\n"
f"[{params['branding']}]\033[91mWarning\033[0m If you used the one-click installer, paste the command above in the terminal window launched after running the cmd_ script. On Windows, that's cmd_windows.bat."
)
raise
@@ -62,7 +62,9 @@ try:
from modules.utils import gradio
# This is set to check if the script is being run within text generation webui or as a standalone script. False is running as part of text gen web ui or a gradio interface
running_in_standalone = False
output_folder_wav = params["output_folder_wav"]
except ModuleNotFoundError:
output_folder_wav = params["output_folder_wav_standalone"]
print(f"[{params['branding']}Startup] Running script.py in standalone mode")
# This is set to check if the script is being run within text generation webui or as a standalone script. true means standalone
running_in_standalone = True
@@ -108,7 +110,6 @@ def delete_old_files(folder_path, days_to_keep):
# Extract settings using params dictionary
delete_output_wavs_setting = params["delete_output_wavs"]
output_folder_wav = params["output_folder_wav"]
output_folder_wav = os.path.normpath(output_folder_wav)
# Check and perform file deletion
@@ -551,15 +552,10 @@ def output_modifier(string, state):
else:
cleaned_part = html.unescape(part.replace('< ', '').replace('< ', '').replace('< ', ''))
voice_to_use = params["narrator_voice"]
# Check if character name exists and if not, just call it TTSOUT_
if "character_menu" in state:
output_file = Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}_{i}.wav')
else:
output_file = Path(f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}_{i}.wav')
# Generate that TTS and output to a file
output_file_str = output_file.as_posix()
output_filename = get_output_filename(state)
generate_response = send_generate_request(
cleaned_part, voice_to_use, language_code, output_file_str
cleaned_part, voice_to_use, language_code, output_filename
)
audio_path = generate_response.get("data", {}).get("audio_path")
audio_files_paragraph.append(audio_path)
@@ -580,14 +576,9 @@ def output_modifier(string, state):
)
cleaned_part = html.unescape(processed_string)
# Process the part and give it a non-character name if being used vai API or standalone.
if "character_menu" in state:
output_file = Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav')
else:
output_file = Path(f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav')
output_file_str = output_file.as_posix()
output_file = get_output_filename(state)
output_filename = get_output_filename(state)
generate_response = send_generate_request(
cleaned_part, params["voice"], language_code, output_file_str
cleaned_part, params["voice"], language_code, output_filename
)
audio_path = generate_response.get("data", {}).get("audio_path")
final_output_file = audio_path
@@ -627,9 +618,11 @@ def output_modifier(string, state):
def get_output_filename(state):
return Path(
f'{params["output_folder_wav"]}/{state["character_menu"]}_{str(uuid.uuid4())[:8]}.wav'
).as_posix()
# Check if character name exists and if not, just call it TTSOUT_
if "character_menu" in state:
return Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav').as_posix()
else:
return Path(f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav').as_posix()
###############################################