init commit

.dockerignore

+# The .dockerignore file excludes files from the container build process.
+#
+# https://docs.docker.com/engine/reference/builder/#dockerignore-file
+
+# Exclude Git files
+.git
+.github
+.gitignore
+
+# Exclude Python cache files
+__pycache__
+.mypy_cache
+.pytest_cache
+.ruff_cache
+
+# Exclude Python virtual environment
+/venv

.github/workflows/push.yaml

+name: Push to Replicate
+
+on:
+  # Workflow dispatch allows you to manually trigger the workflow from GitHub.com
+  # Go to your repo, click "Actions", click "Push to Replicate", click "Run workflow"
+  workflow_dispatch:
+    inputs:
+      model_name:
+        description: 'Enter the model name, like "alice/bunny-detector". If unset, this will default to the value of `image` in cog.yaml.'
+  # # Uncomment these lines to trigger the workflow on every push to the main branch
+  # push:
+  #   branches:
+  #     - main
+
+jobs:
+  push_to_replicate:
+    name: Push to Replicate
+
+    # If your model is large, the default GitHub Actions runner may not 
+    # have enough disk space. If you need more space you can set up a 
+    # bigger runner on GitHub.
+    runs-on: ubuntu-latest
+
+    steps:
+      # This action cleans up disk space to make more room for your
+      # model code, weights, etc.
+      - name: Free disk space
+        uses: jlumbroso/free-disk-space@v1.3.1
+        with:
+          tool-cache: false
+          docker-images: false
+
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      # This action installs Docker buildx and Cog (and optionally CUDA)
+      - name: Setup Cog
+        uses: replicate/setup-cog@v2
+        with:
+          # If you set REPLICATE_API_TOKEN in your GitHub repository secrets,
+          # the action will authenticate with Replicate automatically so you
+          # can push your model
+          token: ${{ secrets.REPLICATE_API_TOKEN }}
+
+      # If you trigger the workflow manually, you can specify the model name.
+      # If you leave it blank (or if the workflow is triggered by a push), the 
+      # model name will be derived from the `image` value in cog.yaml.
+      - name: Push to Replicate
+        run: |
+          if [ -n "${{ inputs.model_name }}" ]; then
+            cog push r8.im/${{ inputs.model_name }}
+          else
+            cog push
+          fi

.gitignore

+.vscode
+__pycache__
+.cog

cog.yaml

+# Configuration for Cog ⚙️
+# Reference: https://cog.run/yaml
+
+build:
+  # set to true if your model requires a GPU
+  gpu: true
+
+  # a list of ubuntu apt packages to install
+  system_packages:
+    - ffmpeg
+
+  # python version in the form '3.11' or '3.11.4'
+  python_version: "3.11.4"
+
+  # a list of packages in the format <package-name>==<version>
+  python_packages:
+    - numpy==1.23.5
+    - torch==2.0.1
+    - torchaudio
+    - funasr
+    - modelscope
+    - huggingface
+    - huggingface_hub
+
+  # commands run after the environment is setup
+  run:
+    - "echo env is ready!"
+    - "echo another command if needed"
+
+# predict.py defines how predictions are run on your model
+predict: "predict.py:Predictor"

predict.py

+# Prediction interface for Cog ⚙️
+# https://cog.run/python
+
+from cog import BasePredictor, Input, Path, BaseModel
+from funasr import AutoModel
+# from modelscope import snapshot_download
+from typing import List
+
+
+class ModelOutput(BaseModel):
+    key: str
+    text: str
+
+
+class Predictor(BasePredictor):
+    def setup(self) -> None:
+        """Load the model into memory to make running multiple predictions efficient"""
+        # model_dir = snapshot_download(
+        #     'iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx')
+        # vad_dir = snapshot_download(
+        #     'iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx')
+
+        # punc_dir = snapshot_download(
+        #     'iic/punc_ct-transformer_cn-en-common-vocab471067-large-onnx')
+
+        self.model = AutoModel(
+            model="paraformer-zh",  vad_model="fsmn-vad", punc_model="ct-punc")
+
+    def predict(
+        self,
+        batch_size: int = Input(description="BatchSize input", default=300),
+        awv: Path = Input(description="Grayscale input awv",
+                          default="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"),
+    ) -> List[str]:
+        try:
+            print("batch_size:", batch_size)
+            print("awv:", awv)
+            res = self.model.generate(
+                input=str(awv), batch_size_s=batch_size)
+            print("res:", res)
+            output_list = []
+            for item in res:
+                text = item['text']
+                output_list.append(text)
+            return output_list
+        except Exception as e:
+            print(f"{e}")
+            return []

test.py

+from funasr import AutoModel
+from modelscope import snapshot_download
+
+
+# model_dir = snapshot_download(
+#     'iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online')
+
+# print("model_dir:", model_dir)
+model = AutoModel(
+    model="/root/.cache/modelscope/hub/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+
+res = model.generate(
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
+print(res)