| license: apache-2.0 | |
| datasets: | |
| - Murple/ksponspeech | |
| language: | |
| - ko | |
| metrics: | |
| - cer | |
| - wer | |
| pipeline_tag: automatic-speech-recognition | |
| # Whisper-Medium-KsponSpeech | |
| The Whisper-medium Model finetunned with [KsponSpeech](https://huggingface.co/datasets/Murple/ksponspeech) | |
| ### Model Description | |
| <!-- Provide a longer summary of what this model is. --> | |
| - **Developed by :** [yw0nam](https://github.com/yw0nam) | |
| - **Shared by :** [yw0nam](https://github.com/yw0nam) | |
| - **Model type :** ASR | |
| - **License:** [apache-2.0] | |
| ## 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 | | |