first

speech_to_speech/LLM/utils.py

@@ -0,0 +1,75 @@
+import base64
+import io
+import re
+from typing import Optional
+
+import requests  # type: ignore[import-untyped]
+from PIL import Image
+
+SMART_PUNCT_TRANSLATION = str.maketrans(
+    {
+        "\u2018": "'",
+        "\u2019": "'",
+        "\u201c": '"',
+        "\u201d": '"',
+    }
+)
+
+SPEECHABLE_PATTERN = re.compile(
+    r"[^\w\s.,!?;:'\"\-()\/\\@#%&*+=$€£¥₹₽¢\[\]{}<>~`^|…—–\n\r\t]",
+    flags=re.UNICODE,
+)
+
+
+def remove_unspeechable(text: str) -> str:
+    """Keep only speechable characters: letters, digits, punctuation, whitespace.
+    support unicode characters (english, arabic, chinese, japanese, korean, etc.)
+    """
+    text = text.translate(SMART_PUNCT_TRANSLATION)
+    return SPEECHABLE_PATTERN.sub("", text)
+
+
+WHISPER_LANGUAGE_TO_LLM_LANGUAGE = {
+    "en": "english",
+    "fr": "french",
+    "es": "spanish",
+    "zh": "chinese",
+    "ja": "japanese",
+    "ko": "korean",
+    "hi": "hindi",
+    "de": "german",
+    "pt": "portuguese",
+    "pl": "polish",
+    "it": "italian",
+    "nl": "dutch",
+}
+
+
+def resolve_auto_language(language_code: Optional[str]) -> tuple[Optional[str], Optional[str]]:
+    """Strip the ``-auto`` suffix and resolve the human-readable language name.
+
+    Returns ``(clean_code, language_name)``.  ``language_name`` is non-None
+    when the code (with or without ``-auto``) maps to a known language.
+    """
+    if not language_code:
+        return language_code, None
+    if language_code.endswith("-auto"):
+        language_code = language_code[:-5]
+    if language_code not in WHISPER_LANGUAGE_TO_LLM_LANGUAGE:
+        return language_code, None
+    return language_code, WHISPER_LANGUAGE_TO_LLM_LANGUAGE.get(language_code)
+
+
+def image_url_to_pil(image_url: str) -> Image.Image:
+    """Convert an image URL or base64 data URI to a PIL Image.
+
+    Accepts:
+    - 'data:image/...;base64,<b64>' data URIs
+    - 'https://...`` or ``http://...' URLs (fetched with a 10s timeout)
+    """
+    if image_url.startswith("data:"):
+        _, b64_data = image_url.split(",", 1)
+        return Image.open(io.BytesIO(base64.b64decode(b64_data)))
+    resp = requests.get(image_url, timeout=10)
+    resp.raise_for_status()
+    return Image.open(io.BytesIO(resp.content))