german tts

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,13 @@
----
-title: German TTS
-emoji: 🐢
-colorFrom: green
-colorTo: red
-sdk: gradio
-sdk_version: 5.3.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Technical Vocabulary
+emoji: 👁
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 5.1.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,71 @@
+import gradio as gr
+import torch
+import os
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+from datasets import load_dataset, Audio
+import numpy as np
+from speechbrain.inference import EncoderClassifier
+
+# Load models and processor
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+model = SpeechT5ForTextToSpeech.from_pretrained("tdnathmlenthusiast/speecht5_finetuned_German_dataset")
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+
+# Load speaker encoder
+device = "cuda" if torch.cuda.is_available() else "cpu"
+speaker_model = EncoderClassifier.from_hparams(
+    source="speechbrain/spkrec-xvect-voxceleb",
+    run_opts={"device": device},
+    savedir=os.path.join("/tmp", "speechbrain/spkrec-xvect-voxceleb")
+)
+
+def create_speaker_embedding(waveform):
+    with torch.no_grad():
+        speaker_embeddings = speaker_model.encode_batch(torch.tensor(waveform))
+        speaker_embeddings = torch.nn.functional.normalize(speaker_embeddings, dim=2)
+        speaker_embeddings = speaker_embeddings.squeeze().cpu().numpy()
+    return speaker_embeddings
+
+# Load a sample from the dataset for speaker embedding
+try:
+    dataset = load_dataset(""Thorsten-Voice/TV-44kHz-Full", "TV-2023.09-Hessisch", split="train", trust_remote_code=True)
+    dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
+    sample = dataset[10]
+    speaker_embedding = create_speaker_embedding(sample['audio']['array'])
+except Exception as e:
+    print(f"Error loading dataset: {e}")
+    # Use a random speaker embedding as fallback
+    speaker_embedding = torch.randn(1, 512)
+
+
+def text_to_speech(text):
+    # Clean up text
+    replacements = [
+    ("0", "zero"),
+    ("1", "one"),
+    ("2", "two"),
+    ("3", "three"),
+    ("4", "four"),
+    ("5", "five"),
+    ("6", "six"),
+    ("7", "seven"),
+    ("8", "eight"),
+    ("9", "nine"),
+    ("_", " ")
+    ]
+    for src, dst in replacements:
+        text = text.replace(src, dst)
+
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(inputs["input_ids"], speaker_embedding, vocoder=vocoder)
+    return (16000, speech.numpy())
+
+iface = gr.Interface(
+    fn=text_to_speech,
+    inputs="text",
+    outputs="audio",
+    title="German Text-to-Speech Using T5 by Tirtha Debnath ",
+    description="Enter German text to convert to speech"
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,15 @@
+pip
+git+https://github.com/huggingface/transformers.git
+accelerate
+datasets
+soundfile
+speechbrain
+torch
+gradio
+spaces
+python_multipart
+huggingface-hub
+hf-transfer
+protobuf
+click
+pydantic