From e2fdb9802abd32e9e82e828b32bfd9e90c0822b2 Mon Sep 17 00:00:00 2001 From: Marius Drechsler Date: Wed, 7 Jan 2026 19:30:05 +0100 Subject: [PATCH] Initial commit --- .gitignore | 3 +++ .gitmodules | 3 +++ README.md | 10 ++++++++++ ansage.py | 33 +++++++++++++++++++++++++++++++++ coqui-ai-TTS | 1 + requirements.txt | 1 + 6 files changed, 51 insertions(+) create mode 100644 .gitignore create mode 100644 .gitmodules create mode 100644 README.md create mode 100644 ansage.py create mode 160000 coqui-ai-TTS create mode 100644 requirements.txt diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..542c2cb --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +.direnv/ +.envrc +*.wav diff --git a/.gitmodules b/.gitmodules new file mode 100644 index 0000000..ecec5df --- /dev/null +++ b/.gitmodules @@ -0,0 +1,3 @@ +[submodule "coqui-ai-TTS"] + path = coqui-ai-TTS + url = https://github.com/idiap/coqui-ai-TTS diff --git a/README.md b/README.md new file mode 100644 index 0000000..73ee0e0 --- /dev/null +++ b/README.md @@ -0,0 +1,10 @@ +# BahnansagenTTS + + +## Project Setup + +1. Install python3.12 and ffmpeg7.0 +2. ```git submodule init``` +3. ```cd coqui-ai-TTS && pip install -e .``` +4. ```pip install -r requirements.txt``` in project root +5. Profit diff --git a/ansage.py b/ansage.py new file mode 100644 index 0000000..3a5a52d --- /dev/null +++ b/ansage.py @@ -0,0 +1,33 @@ +import torch +from TTS.api import TTS + +# Get device +device = "cuda" if torch.cuda.is_available() else "cpu" + +# List available 🐸TTS models +print(TTS().list_models()) + +# Initialize TTS +tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device) + +# List speakers +print(tts.speakers) + +# Run TTS +# ❗ XTTS supports both, but many models allow only one of the `speaker` and +# `speaker_wav` arguments + +# TTS with list of amplitude values as output, clone the voice from `speaker_wav` +#wav = tts.tts( +# text="Hello world!", +# speaker_wav="my/cloning/audio.wav", +# language="en" +#) + +# TTS to a file, use a preset speaker +tts.tts_to_file( + text="Hallo Oliver, herzlichen Glückwunsch zur erfolgreichen Entlastung", + speaker_wav="./0248.wav", + language="en", + file_path="output2.wav" +) diff --git a/coqui-ai-TTS b/coqui-ai-TTS new file mode 160000 index 0000000..d72c0d5 --- /dev/null +++ b/coqui-ai-TTS @@ -0,0 +1 @@ +Subproject commit d72c0d539b1e6d5880084d8a18a3e489de331075 diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..6d6fe55 --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +torchaudio==2.6