Add translation example from chinese, french to english (#681)

This adds:
- a VAD node to detect voice within an audio to avoid having too much
noise
- Bump distil-whisper to whisper-turbo
- Use Argotranslate and OPUS-MT for translation
- Add example dataflow within the example folder

## Get started

```bash
cd examples/translation
dora up

dora build dataflow_zh_en_terminal.yml
dora start dataflow_zh_en_terminal.yml --detach

python pretty_print.py
```

examples/translation/.gitignore

@@ -0,0 +1 @@
+*.pt

examples/translation/README.md

@@ -0,0 +1,24 @@
+# Dora argo example
+
+Make sure to have, dora, pip and cargo installed.
+
+```bash
+dora up
+
+## For chinese
+dora build dataflow_zh_en_terminal.yml
+dora start dataflow_zh_en_terminal.yml --detach
+
+python pretty_print.py
+
+dora stop
+
+
+## For chinese
+dora build dataflow_en_zh_terminal.yml
+dora start dataflow_en_zh_terminal.yml --detach
+
+python pretty_print.py
+
+dora stop
+```

examples/translation/dataflow_en_zh.yml

@@ -0,0 +1,45 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: english
+      TRANSLATE: false
+
+  - id: dora-argotranslate
+    build: pip install -e ../../node-hub/dora-argotranslate
+    path: dora-argotranslate
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: en
+      TARGET_LANGUAGE: zh
+
+  - id: dora-rerun
+    build: cargo build -p dora-rerun --release
+    path: dora-rerun
+    inputs:
+      text: dora-argotranslate/text
+    env:
+      IMAGE_WIDTH: 640
+      IMAGE_HEIGHT: 480

examples/translation/dataflow_en_zh_terminal.yml

@@ -0,0 +1,45 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: english
+      TRANSLATE: false
+
+  - id: dora-opus
+    build: pip install -e ../../node-hub/dora-opus
+    path: dora-opus
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: en
+      TARGET_LANGUAGE: zh
+
+  - id: pretty-print
+    path: dynamic
+    inputs:
+      translated_text: dora-opus/text
+      original_text: dora-distil-whisper/text
+    env:
+      IMAGE_WIDTH: 640
+      IMAGE_HEIGHT: 480

examples/translation/dataflow_en_zh_terminal_argo.yml

@@ -0,0 +1,46 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: english
+      TRANSLATE: false
+
+  - id: dora-argotranslate
+    build: pip install -e ../../node-hub/dora-argotranslate
+    path: dora-argotranslate
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: en
+      TARGET_LANGUAGE: zh
+
+  - id: pretty-print
+    build: cargo build -p dora-rerun --release
+    path: dynamic
+    inputs:
+      translated_text: dora-argotranslate/text
+      original_text: dora-distil-whisper/text
+    env:
+      IMAGE_WIDTH: 640
+      IMAGE_HEIGHT: 480

examples/translation/dataflow_fr_en.yml

@@ -0,0 +1,46 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: french
+      TRANSLATE: false
+
+  - id: dora-argotranslate
+    build: pip install -e ../../node-hub/dora-argotranslate
+    path: dora-argotranslate
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: fr
+      TARGET_LANGUAGE: en
+
+  - id: dora-rerun
+    build: cargo build -p dora-rerun --release
+    path: dora-rerun
+    inputs:
+      translated_text: dora-argotranslate/text
+      original_text: dora-distil-whisper/text
+    env:
+      IMAGE_WIDTH: 640
+      IMAGE_HEIGHT: 480

examples/translation/dataflow_zh_en.yml

@@ -0,0 +1,46 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: chinese
+      TRANSLATE: false
+
+  - id: dora-opus
+    build: pip install -e ../../node-hub/dora-opus
+    path: dora-opus
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: zh
+      TARGET_LANGUAGE: en
+
+  - id: plot
+    build: cargo build -p dora-rerun --release
+    path: dora-rerun
+    inputs:
+      translated_text: dora-opus/text
+      original_text: dora-distil-whisper/text
+    env:
+      IMAGE_WIDTH: 640
+      IMAGE_HEIGHT: 480

examples/translation/dataflow_zh_en_terminal.yml

@@ -0,0 +1,42 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-vad
+    build: pip install -e ../../node-hub/dora-vad
+    path: dora-vad
+    inputs:
+      audio: dora-microphone/audio
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-vad/audio
+    outputs:
+      - text
+    env:
+      TARGET_LANGUAGE: chinese
+      TRANSLATE: false
+
+  - id: dora-opus
+    build: pip install -e ../../node-hub/dora-opus
+    path: dora-opus
+    inputs:
+      text: dora-distil-whisper/text
+    outputs:
+      - text
+    env:
+      SOURCE_LANGUAGE: zh
+      TARGET_LANGUAGE: en
+
+  - id: pretty-print
+    path: dynamic
+    inputs:
+      translated_text: dora-opus/text
+      original_text: dora-distil-whisper/text

examples/translation/pretty_print.py

@@ -0,0 +1,46 @@
+import os
+import shutil
+
+
+def clear_screen():
+    # Clear the screen based on the operating system
+    os.system("cls" if os.name == "nt" else "clear")
+
+
+def print_centered(texts):
+    # Get terminal size
+    terminal_size = shutil.get_terminal_size()
+
+    # Print newlines to move cursor to the middle vertically
+    for k, v in texts.items():
+        print(k)
+        print("\n" * 1)
+        # Calculate horizontal padding and print the centered text
+        for l in v:
+            print(l.center(terminal_size.columns))
+        print("\n" * 1)
+
+
+from dora import Node
+
+node = Node("pretty-print")
+
+previous_texts = {}
+
+clear_screen()
+print("Waiting for speech...")
+for event in node:
+    if event["type"] == "INPUT":
+        # The sentence to be printed
+        sentence = event["value"][0].as_py()
+        if event["id"] not in previous_texts.keys():
+
+            previous_texts[event["id"]] = ["", "", sentence]
+        else:
+            previous_texts[event["id"]] += [sentence]
+            previous_texts[event["id"]] = previous_texts[event["id"]][-3:]
+        # Clear the screen
+        clear_screen()
+
+        # Print the sentence in the middle of the terminal
+        print_centered(previous_texts)

node-hub/dora-argotranslate/README.md

@@ -0,0 +1,2 @@
+# Dora text translation Node using Argo translate
+

node-hub/dora-argotranslate/dora_argotranslate/__init__.py

@@ -0,0 +1,11 @@
+import os
+
+# Define the path to the README file relative to the package directory
+readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
+
+# Read the content of the README file
+try:
+    with open(readme_path, "r", encoding="utf-8") as f:
+        __doc__ = f.read()
+except FileNotFoundError:
+    __doc__ = "README file not found."