From 1761b21f06ffd276ad042f42c5889a88bcbe6d19 Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Thu, 2 Jan 2025 09:52:05 +0800
Subject: [PATCH] Upload matcha tts models for ljspeech

---
 .github/scripts/ljspeech/TTS/run-matcha.sh | 31 ++++++++++
 .github/workflows/ljspeech.yml             | 68 ++++++++++++++++++++++
 egs/ljspeech/TTS/matcha/export_onnx.py     |  4 ++
 3 files changed, 103 insertions(+)

diff --git a/.github/scripts/ljspeech/TTS/run-matcha.sh b/.github/scripts/ljspeech/TTS/run-matcha.sh
index 954dd5bd8..f56b101b8 100755
--- a/.github/scripts/ljspeech/TTS/run-matcha.sh
+++ b/.github/scripts/ljspeech/TTS/run-matcha.sh
@@ -115,6 +115,37 @@ function export_onnx() {
 
   ls -lh /icefall/*.wav
   soxi /icefall/generated-matcha-tts-steps-6-*.wav
+
+  cp ./model-steps-*.onnx /icefall
+
+  d=matcha-icefall-en_US-ljspeech
+  mkdir $d
+  cp -v data/tokens.txt $d
+  cp model-steps-3.onnx $d
+  pushd $d
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/espeak-ng-data.tar.bz2
+  tar xf espeak-ng-data.tar.bz2
+  rm espeak-ng-data.tar.bz2
+
+cat >README.md <<EOF
+# Introduction
+
+This model is trained using the dataset from
+https://keithito.com/LJ-Speech-Dataset/
+
+The dataset contains only 1 female speaker.
+
+You can find the training code at
+https://github.com/k2-fsa/icefall/tree/master/egs/ljspeech/TTS#matcha
+EOF
+
+  ls -lh
+
+  popd
+
+  tar cvjf $d.tar.bz2 $d
+  mv $d.tar.bz2 /icefall
+  mv $d /icefall
 }
 
 prepare_data
diff --git a/.github/workflows/ljspeech.yml b/.github/workflows/ljspeech.yml
index 7dca96b37..c5ecff0f9 100644
--- a/.github/workflows/ljspeech.yml
+++ b/.github/workflows/ljspeech.yml
@@ -94,3 +94,71 @@ jobs:
           repo_name: k2-fsa/sherpa-onnx
           repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
           tag: tts-models
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: generated-test-files-${{ matrix.python-version }}-${{ matrix.torch-version }}
+          path: ./*.wav
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: step-2
+          path: ./model-steps-2.onnx
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: step-3
+          path: ./model-steps-3.onnx
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: step-4
+          path: ./model-steps-4.onnx
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: step-5
+          path: ./model-steps-5.onnx
+
+      - uses: actions/upload-artifact@v4
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0'
+        with:
+          name: step-6
+          path: ./model-steps-6.onnx
+
+      - name: Upload models to huggingface
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0' && github.event_name == 'push'
+        shell: bash
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          d=matcha-icefall-en_US-ljspeech
+
+          GIT_LFS_SKIP_SMUDGE=1  git clone https://huggingface.co/csukuangfj/$d hf
+          cp -av $d/* hf/
+
+          pushd hf
+          git add .
+
+          git config --global user.name "csukuangfj"
+          git config --global user.email "csukuangfj@gmail.com"
+          git config --global lfs.allowincompletepush true
+
+          git commit -m "upload model" && git push https://csukuangfj:${HF_TOKEN}@huggingface.co/csukuangfj/$d main || true
+          popd
+
+      - name: Release exported onnx models
+        if: matrix.python-version == '3.9' && matrix.torch-version == '2.3.0' && github.event_name == 'push'
+        uses: svenstaro/upload-release-action@v2
+        with:
+          file_glob: true
+          overwrite: true
+          file: matcha-icefall-*.tar.bz2
+          repo_name: k2-fsa/sherpa-onnx
+          repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
+          tag: tts-models
diff --git a/egs/ljspeech/TTS/matcha/export_onnx.py b/egs/ljspeech/TTS/matcha/export_onnx.py
index 39709cc36..e64409802 100755
--- a/egs/ljspeech/TTS/matcha/export_onnx.py
+++ b/egs/ljspeech/TTS/matcha/export_onnx.py
@@ -176,12 +176,16 @@ def main():
             "language": "English",
             "voice": "en-us",
             "has_espeak": 1,
+            "jieba": 0,
             "n_speakers": 1,
             "sample_rate": 22050,
             "version": 1,
+            "pad_id": params.pad_id,
             "model_author": "icefall",
             "maintainer": "k2-fsa",
+            "use_eos_bos": 0,
             "dataset": "LJ Speech",
+            "dataset_url": "https://keithito.com/LJ-Speech-Dataset/",
             "num_ode_steps": num_steps,
         }
         add_meta_data(filename=filename, meta_data=meta_data)