oxide-lab
/

whisper-tiny-GGUF

Automatic Speech Recognition

speech-recognition

Model card Files Files and versions

FerrisMind commited on Jan 30

Commit

49a46f0

·

verified ·

1 Parent(s): 2738107

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -93,7 +93,7 @@ For most use cases, we recommend **q4_k** format as it provides the best balance
 - **Source Model**: [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
 - **Quantization Methods**:
-  - **Candle GGUF** (root directory): Python-based quantization via `convert_whisper_to_gguf.py`
     - Adds `model.` prefix to tensor names for Candle compatibility
   - **whisper.cpp GGML** (whisper.cpp/ subdirectory): whisper-quantize tool
     - Uses original tensor names without prefix

 - **Source Model**: [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
 - **Quantization Methods**:
+  - **Candle GGUF** (root directory): Python-based quantization. Directly PyTorch → GGUF
     - Adds `model.` prefix to tensor names for Candle compatibility
   - **whisper.cpp GGML** (whisper.cpp/ subdirectory): whisper-quantize tool
     - Uses original tensor names without prefix