Initial commit

.gitignore

@@ -0,0 +1,3 @@
+.direnv/
+.envrc
+*.wav

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "coqui-ai-TTS"]
+	path = coqui-ai-TTS
+	url = https://github.com/idiap/coqui-ai-TTS

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

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"
+)

coqui-ai-TTS

@@ -0,0 +1 @@
+Subproject commit d72c0d539b1e6d5880084d8a18a3e489de331075

requirements.txt

@@ -0,0 +1 @@
+torchaudio==2.6