bigdefence
/

Bigvox-Midm-Audio

Audio-Text-to-Text

omni_speech_midm

Model card Files Files and versions

bigdefence commited on Jul 31, 2025

Commit

2d35108

·

verified ·

1 Parent(s): ba40c37

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -100,7 +100,7 @@ git clone https://huggingface.co/bigdefence/Bigvox-Midm-Audio
    - [HuggingFace](https://huggingface.co/openai/whisper-large-v3)에서 **Whisper-large-v3** 음성 인코더를 다운로드하여 `./models/speech_encoder/` 디렉토리에 배치 🎤
 2. **추론 실행**:
-   - **음성-텍스트(S2T)** 추론:
      **Non-streaming**
      ```bash
      python3 omni_speech/infer/bigvox.py --query_audio test_audio.wav

    - [HuggingFace](https://huggingface.co/openai/whisper-large-v3)에서 **Whisper-large-v3** 음성 인코더를 다운로드하여 `./models/speech_encoder/` 디렉토리에 배치 🎤
 2. **추론 실행**:
+   - **음성-텍스트(S2T)** 추론:<br>
      **Non-streaming**
      ```bash
      python3 omni_speech/infer/bigvox.py --query_audio test_audio.wav