v2.2.0, now adds language name to folder when explicitly set

README.md

@@ -147,6 +147,7 @@ is closed then to get back into the environment `cd transcribe_anything` and exe
   * All tests are run by `tox`, simply go to the project directory root and run it.
 
 # Versions
+  * 2.2.0: Now explictly setting a language will put the file in a folder with that language name, allowing multi language passes without overwriting.
   * 2.1.2: yt-dlp pinned to new minimum version. Fixes downloading issues from old lib. Adds audio normalization by default.
   * 2.1.1: Updates keywords for easier pypi finding.
   * 2.1.0: Unknown args are now assumed to be for whisper and passed to it as-is. Fixes https://github.com/zackees/transcribe-anything/issues/3

setup.py

@@ -16,7 +16,7 @@
 EMAIL = "dont@email.me"
 AUTHOR = "Zach Vorhies"
 REQUIRES_PYTHON = ">=3.9.0"
-VERSION = "2.1.2"
+VERSION = "2.2.0"
 
 # The text of the README file
 with open(os.path.join(HERE, "README.md"), encoding="utf-8", mode="r") as fd:

tests/test_transcribe_anything.py

@@ -45,6 +45,13 @@ def test_initial_prompt(self) -> None:
             ],
             cwd=LOCALFILE_DIR,
         )
+        # Expect that when the language is explicitly set that the output file ends up in
+        # that language folder.
+        expected_output = os.path.join(LOCALFILE_DIR, "video", "en", "out.txt")
+        self.assertTrue(
+            os.path.exists(expected_output),
+            f"Path {expected_output} doesn't exist, instead it was {os.listdir(LOCALFILE_DIR)}",  # pylint: disable=line-too-long
+        )
 
     def test_fetch_command_installed(self) -> None:
         """Check that the command works on a live short video."""

transcribe_anything/api.py

@@ -42,7 +42,9 @@ def transcribe(
         # https://example.com/, which will yield a basename of "".
         basename = os.path.basename(os.path.dirname(url_or_file))
         basename = sanitize_path(basename)
+    output_dir_was_generated = False
     if output_dir is None:
+        output_dir_was_generated = True
         if url_or_file.startswith("http"):
             # Try and the title of the video using yt-dlp
             # If that fails, use the basename of the url
@@ -60,6 +62,8 @@ def transcribe(
                 output_dir = basename
         else:
             output_dir = os.path.splitext(basename)[0]
+    if output_dir_was_generated and language is not None:
+        output_dir = os.path.join(output_dir, language)
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.makedirs(output_dir, exist_ok=True)