Add support for GigaAM-CTC-v2 (#2135)

Related to #2098.

@@ -79,6 +79,31 @@ jobs:
 
 
           tar cjvf ${d}.tar.bz2 $d
           tar cjvf ${d}.tar.bz2 $d
 
 
+      - name: Run CTC v2
+        shell: bash
+        run: |
+          pushd scripts/nemo/GigaAM
+          ./run-ctc-v2.sh
+          popd
+
+          d=sherpa-onnx-nemo-ctc-giga-am-v2-russian-2025-04-19
+          mkdir $d
+          mkdir $d/test_wavs
+          rm scripts/nemo/GigaAM/v2_ctc.onnx
+          mv -v scripts/nemo/GigaAM/*.int8.onnx $d/
+          cp -v scripts/nemo/GigaAM/LICENCE $d/
+          mv -v scripts/nemo/GigaAM/tokens.txt $d/
+          mv -v scripts/nemo/GigaAM/*.wav $d/test_wavs/
+          mv -v scripts/nemo/GigaAM/run-ctc.sh $d/
+          mv -v scripts/nemo/GigaAM/*-ctc-v2.py $d/
+
+          ls -lh scripts/nemo/GigaAM/
+
+          ls -lh $d
+
+          tar cjvf ${d}.tar.bz2 $d
+
+
       - name: Release
       - name: Release
         uses: svenstaro/upload-release-action@v2
         uses: svenstaro/upload-release-action@v2
         with:
         with:
@@ -114,3 +139,29 @@ jobs:
             git status
             git status
             git commit -m "add models"
             git commit -m "add models"
             git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main
             git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main
+
+      - name: Publish v2 to huggingface (Transducer)
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        uses: nick-fields/retry@v3
+        with:
+          max_attempts: 20
+          timeout_seconds: 200
+          shell: bash
+          command: |
+            git config --global user.email "csukuangfj@gmail.com"
+            git config --global user.name "Fangjun Kuang"
+
+            d=sherpa-onnx-nemo-transducer-giga-am-v2-russian-2025-04-19/
+            export GIT_LFS_SKIP_SMUDGE=1
+            export GIT_CLONE_PROTECTION_ACTIVE=false
+            git clone https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d huggingface
+            mv -v $d/* ./huggingface
+            cd huggingface
+            git lfs track "*.onnx"
+            git lfs track "*.wav"
+            git status
+            git add .
+            git status
+            git commit -m "add models"
+            git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main

+import gigaam
+import onnx
+import torch
+from onnxruntime.quantization import QuantType, quantize_dynamic
+
+
+def add_meta_data(filename: str, meta_data: dict[str, str]):
+    """Add meta data to an ONNX model. It is changed in-place.
+
+    Args:
+      filename:
+        Filename of the ONNX model to be changed.
+      meta_data:
+        Key-value pairs.
+    """
+    model = onnx.load(filename)
+    while len(model.metadata_props):
+        model.metadata_props.pop()
+
+    for key, value in meta_data.items():
+        meta = model.metadata_props.add()
+        meta.key = key
+        meta.value = str(value)
+
+    onnx.save(model, filename)
+
+
+def main() -> None:
+    model_name = "v2_ctc"
+    model = gigaam.load_model(model_name, fp16_encoder=False, use_flash=False, download_root=".")
+    with open("./tokens.txt", "w", encoding="utf-8") as f:
+        for i, s in enumerate(model.cfg["labels"]):
+            f.write(f"{s} {i}\n")
+        f.write(f"<blk> {i+1}\n")
+        print("Saved to tokens.txt")
+    model.to_onnx(".")
+    meta_data = {
+        "vocab_size": len(model.cfg["labels"]) + 1,
+        "normalize_type": "",
+        "subsampling_factor": 4,
+        "model_type": "EncDecCTCModel",
+        "version": "1",
+        "model_author": "https://github.com/salute-developers/GigaAM",
+        "license": "https://github.com/salute-developers/GigaAM/blob/main/LICENSE",
+        "language": "Russian",
+        "is_giga_am": 1,
+    }
+    add_meta_data(f"./{model_name}.onnx", meta_data)
+    quantize_dynamic(
+        model_input=f"./{model_name}.onnx",
+        model_output="./model.int8.onnx",
+        weight_type=QuantType.QUInt8,
+    )
+
+
+if __name__ == '__main__':
+    main()

+#!/usr/bin/env bash
+
+set -ex
+
+function install_gigaam() {
+  curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
+  python3 get-pip.py
+
+  BRANCH='main'
+  python3 -m pip install git+https://github.com/salute-developers/GigaAM.git@$BRANCH#egg=gigaam
+
+  python3 -m pip install -qq kaldi-native-fbank
+}
+
+function download_files() {
+  curl -SL -O https://huggingface.co/csukuangfj/tmp-files/resolve/main/GigaAM/example.wav
+  curl -SL -O https://github.com/salute-developers/GigaAM/blob/main/LICENSE
+}
+
+install_gigaam
+download_files
+
+python3 ./export-onnx-ctc-v2.py
+ls -lh
+python3 ./test-onnx-ctc.py