Downloads · 30 days
49
0% of all-time downloads
whisper-medium-zeroth_korean
spow12/whisper-medium-zeroth_korean
whisper-medium-zeroth_korean is a automatic speech recognition model from spow12. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
The Whisper-medium Model finetunned with KsponSpeech
All-time downloads
11.9K
Public
Parameters
764M
6.1 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 10, 2023
- Updated
- Oct 16, 2024
- SHA
- 5b9e7ee4
Datasets
Model card
From the Hugging Face model README
Whisper-Medium-KsponSpeech
The Whisper-medium Model finetunned with KsponSpeech
Model Description
<!-- Provide a longer summary of what this model is. -->Uses
processor = WhisperProcessor.from_pretrained("openai/whisper-medium", language="ko", task="transcribe")
model = WhisperForConditionalGeneration.from_pretrained('spow12/whisper-medium-zeroth_korean').cuda()
data, _ = librosa.load(wav_path, sr=16000)
input_features = processor(data, sampling_rate=16000, return_tensors="pt").input_features.cuda()
predicted_ids = model.generate(input_features)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
Metrics
| Metric | result |
|---|---|
| WER | 3.96 |
| CER | 1.71 |
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ko
- Created
- May 10, 2023
- Updated
- Oct 16, 2024