Hugging Face's logo

daekeun-ml
/
Phi-4-multimodal-finetune-ko-speech

Safetensors
Korean
phi4mm
korean
stt
custom_code
phi
phi-4-multimodal
Eval Results
Model card Files Community
daekeun-ml commited on
Commit
a780aa8
·
verified ·
1 Parent(s): 0602162

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -57,7 +57,7 @@ This is a fine-tuned model for Korean speech-to-text translation, from [microsof
57
  - kresnik/zeroth_korean
58
  - mozilla-foundation/common_voice_17_0 (Used Korean speech only)
59
  - PolyAI/minds14 (Used Korean speech only)
60
- - Custom dataset on my own. The speech was a mix of fast and slow speech (Technical blog contents and presentations I have posted), with some modulation using [audiomentations](https://github.com/iver56/audiomentations).
61
 
62
  Total 35K samples. Each sample is a pair of Korean speech and its transcription. Dataset was sampled 16kHz.
63
 
 
57
  - kresnik/zeroth_korean
58
  - mozilla-foundation/common_voice_17_0 (Used Korean speech only)
59
  - PolyAI/minds14 (Used Korean speech only)
60
+ - Custom dataset on my own. The speech was a mix of fast and slow speech (Technical blog contents and presentations I have posted), with some modulation using [audiomentations](https://github.com/iver56/audiomentations) and [this script](https://github.com/daekeun-ml/azure-genai-utils/blob/main/azure_genai_utils/stt/augment.py)
61
 
62
  Total 35K samples. Each sample is a pair of Korean speech and its transcription. Dataset was sampled 16kHz.
63