from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
import librosa

processor = AutoProcessor.from_pretrained('spow12/Visual-novel-transcriptor', language="ja", task="transcribe")
model = AutoModelForSpeechSeq2Seq.from_pretrained('spow12/Visual-novel-transcriptor').cuda()
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="ja", task="transcribe")

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)
print(transcription[0])

Bias, Risks, and Limitations

Developed by: spow12(yw_nam)
Shared by: spow12(yw_nam)
Model type: Seq2Seq
Language(s) (NLP): japanese
Finetuned from model: <a href="https://huggingface.co/distil-whisper/distil-large-v2" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">distil-whisper/distil-large-v2 .

This model trained by japanese dataset included visual novel which contain nsfw content.

Use & Credit

This model is currently available for non-commercial use only. Also, since I'm not detailed in licensing, I hope you use it responsibly.

By sharing this model, I hope to contribute to the research efforts of our community (the open-source community and anime persons).

Citation

bibtex

@misc {Visual-novel-transcriptor,
    author       = { YoungWoo Nam },
    title        = { Visual-novel-transcriptor },
    year         = 2024,
    url          = { https://huggingface.co/spow12/Visual-novel-transcriptor },
    publisher    = { Hugging Face }
}