perf/docs: skip language detection step

winstxnhdw · Jul 12, 2024 · c21c9ab · c21c9ab
1 parent 1e5d85e
commit c21c9ab
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -10,7 +10,7 @@
 [![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/winstxnhdw/CapGen)
 [![Open a Pull Request](https://huggingface.co/datasets/huggingface/badges/raw/main/open-a-pr-md-dark.svg)](https://github.com/winstxnhdw/CapGen/compare)
 
-A fast cross-platform CPU-first video/audio transcriber for generating caption files with [Whisper](https://openai.com/research/whisper) and [CTranslate2](https://github.com/OpenNMT/CTranslate2), hosted on Hugging Face Spaces. A `pip` installable offline CLI tool with CUDA support is provided. By default, Voice Activity Detection (VAD) preprocessing is always enabled.
+A fast cross-platform CPU-first video/audio English-only transcriber for generating caption files with [Whisper](https://openai.com/research/whisper) and [CTranslate2](https://github.com/OpenNMT/CTranslate2), hosted on Hugging Face Spaces. A `pip` installable offline CLI tool with CUDA support is provided. By default, Voice Activity Detection (VAD) preprocessing is always enabled.
 
 ## Requirements
 

diff --git a/capgen/transcriber/transcriber.py b/capgen/transcriber/transcriber.py
@@ -70,6 +70,7 @@ def transcribe(self, file: str | BinaryIO, caption_format: str) -> str | None:
         """
         segments, _ = self.model.transcribe(
             file,
+            language='en',
             beam_size=1,
             vad_filter=True,
             vad_parameters={'min_silence_duration_ms': 500},