Duplicate from ahnafsamin/GroTTS-FastSpeech2

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: GroTTS FastSpeech2
+emoji: 📚
+colorFrom: pink
+colorTo: pink
+sdk: gradio
+sdk_version: 3.0.24
+app_file: app.py
+pinned: false
+license: afl-3.0
+duplicated_from: ahnafsamin/GroTTS-FastSpeech2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,42 @@
+import os
+
+os.environ["CURL_CA_BUNDLE"]=""
+
+import gradio as gr
+import time
+import urllib.request
+from pathlib import Path
+import os
+import torch
+import scipy.io.wavfile
+from espnet2.bin.tts_inference import Text2Speech
+from espnet2.utils.types import str_or_none
+from parallel_wavegan.utils import download_pretrained_model
+
+
+gos_text2speech = Text2Speech.from_pretrained(
+  model_tag="https://huggingface.co/ahnafsamin/FastSpeech2-gronings/resolve/main/tts_train_fastspeech2_raw_char_tacotron_train.loss.ave.zip",
+  vocoder_tag="parallel_wavegan/ljspeech_parallel_wavegan.v3"
+)
+
+def inference(text,lang):
+  with torch.no_grad():
+      if lang == "gronings":
+          wav = gos_text2speech(text)["wav"]
+          scipy.io.wavfile.write("out.wav", gos_text2speech.fs , wav.view(-1).cpu().numpy())
+
+  return  "out.wav", "out.wav"
+
+title = "GroTTS"
+examples = [
+  ['Ze gingen mit klas noar waddendiek, over en deur bragel lopen.', 'gronings']
+]
+
+
+gr.Interface(
+    inference,
+    [gr.inputs.Textbox(label="input text", lines=3), gr.inputs.Radio(choices=["gronings"], type="value", default="gronings", label="language")], 
+    [gr.outputs.Audio(type="file", label="Output"), gr.outputs.File()],
+    title=title,
+    examples=examples
+    ).launch(enable_queue=True)

packages.txt

@@ -0,0 +1,2 @@
+cmake
+libsndfile1

requirements.txt

@@ -0,0 +1,7 @@
+espnet==0.10.3 
+pyopenjtalk==0.1.5 
+parallel_wavegan==0.5.3 
+espnet_model_zoo
+scipy
+torch
+numpy==1.23.1