Duplicate from akhaliq/ESPnet2-TTS

Co-authored-by: AK <[email protected]>

.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
+*.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
+*.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 +1,38 @@
+---
+title: ESPnet2 TTS
+emoji: 📈
+colorFrom: green
+colorTo: green
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: akhaliq/ESPnet2-TTS
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import time
+import torch
+import scipy.io.wavfile
+from espnet2.bin.tts_inference import Text2Speech
+from espnet2.utils.types import str_or_none
+
+tagen = 'kan-bayashi/ljspeech_vits' 
+vocoder_tagen = "none" 
+
+text2speechen = Text2Speech.from_pretrained(
+    model_tag=str_or_none(tagen),
+    vocoder_tag=str_or_none(vocoder_tagen),
+    device="cpu",
+    # Only for Tacotron 2 & Transformer
+    threshold=0.5,
+    # Only for Tacotron 2
+    minlenratio=0.0,
+    maxlenratio=10.0,
+    use_att_constraint=False,
+    backward_window=1,
+    forward_window=3,
+    # Only for FastSpeech & FastSpeech2 & VITS
+    speed_control_alpha=1.0,
+    # Only for VITS
+    noise_scale=0.333,
+    noise_scale_dur=0.333,
+)
+
+
+tagjp = 'kan-bayashi/jsut_full_band_vits_prosody' 
+vocoder_tagjp = 'none'
+
+text2speechjp = Text2Speech.from_pretrained(
+    model_tag=str_or_none(tagjp),
+    vocoder_tag=str_or_none(vocoder_tagjp),
+    device="cpu",
+    # Only for Tacotron 2 & Transformer
+    threshold=0.5,
+    # Only for Tacotron 2
+    minlenratio=0.0,
+    maxlenratio=10.0,
+    use_att_constraint=False,
+    backward_window=1,
+    forward_window=3,
+    # Only for FastSpeech & FastSpeech2 & VITS
+    speed_control_alpha=1.0,
+    # Only for VITS
+    noise_scale=0.333,
+    noise_scale_dur=0.333,
+)
+
+tagch = 'kan-bayashi/csmsc_full_band_vits'
+vocoder_tagch = "none" 
+
+text2speechch = Text2Speech.from_pretrained(
+    model_tag=str_or_none(tagch),
+    vocoder_tag=str_or_none(vocoder_tagch),
+    device="cpu",
+    # Only for Tacotron 2 & Transformer
+    threshold=0.5,
+    # Only for Tacotron 2
+    minlenratio=0.0,
+    maxlenratio=10.0,
+    use_att_constraint=False,
+    backward_window=1,
+    forward_window=3,
+    # Only for FastSpeech & FastSpeech2 & VITS
+    speed_control_alpha=1.0,
+    # Only for VITS
+    noise_scale=0.333,
+    noise_scale_dur=0.333,
+)
+
+def inference(text,lang):
+  with torch.no_grad():
+      if lang == "english":
+          wav = text2speechen(text)["wav"]
+          scipy.io.wavfile.write("out.wav",text2speechen.fs , wav.view(-1).cpu().numpy())
+      if lang == "chinese":
+          wav = text2speechch(text)["wav"]
+          scipy.io.wavfile.write("out.wav",text2speechch.fs , wav.view(-1).cpu().numpy())
+      if lang == "japanese":
+          wav = text2speechjp(text)["wav"]
+          scipy.io.wavfile.write("out.wav",text2speechjp.fs , wav.view(-1).cpu().numpy())
+  return  "out.wav"
+title = "ESPnet2-TTS"
+description = "Gradio demo for ESPnet2-TTS: Extending the Edge of TTS Research. To use it, simply add your audio, or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2110.07840' target='_blank'>ESPnet2-TTS: Extending the Edge of TTS Research</a> | <a href='https://github.com/espnet/espnet' target='_blank'>Github Repo</a></p>"
+
+examples=[['This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results',"english"],['レシピの統一された設計により、ユーザーは最先端のE2E-TTSの結果をすばやく再現できます。また、推論用の統合Pythonインターフェースで事前にトレーニングされたモデルを多数提供し、ユーザーがベースラインサンプルを生成してデモを構築するための迅速な手段を提供します。',"japanese"],['对英语和日语语料库的实验评估表明，我们提供的模型合成了与真实情况相当的话语，达到了最先进的水平',"chinese"]]
+
+gr.Interface(
+    inference, 
+    [gr.inputs.Textbox(label="input text",lines=10),gr.inputs.Radio(choices=["english", "chinese", "japanese"], type="value", default="english", label="language")], 
+    gr.outputs.Audio(type="file", label="Output"),
+    title=title,
+    description=description,
+    article=article,
+    enable_queue=True,
+    examples=examples
+    ).launch(debug=True)

packages.txt

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

requirements.txt

@@ -0,0 +1,6 @@
+espnet==0.10.3 
+pyopenjtalk==0.1.5 
+parallel_wavegan==0.5.3 
+espnet_model_zoo
+scipy
+torch