---
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Hibiki_ASR_Phonemizer
  results: []
language:
- ja
---

# Hibiki ASR Phonemizer

This model is a Phoneme Level Speech Recognition network, originally a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on a
mixture of Different Japanese datasets.

it can detect, transcribe and do the following:

- non-speech sounds such as gasp, erotic moans, laughter, etc.
- adding punctuations more faithfully.
Don't use this model without the post processing functions I wrote below, or you'll get less than ideal performance. check the notebook.

__________________________________
to reverse the process and get the graphemes, use [this model](https://huggingface.co/Respair/Japanese_Phoneme_to_Grapheme_LLM). 



__________________________________
## How to use

Check here -> [Notebook](https://colab.research.google.com/drive/13tx8WKzkvePFdtKU4WUE_iYyYCqTY8dZ#scrollTo=5XqUs-sPdT79)

## Intended uses & limitations

No restrictions is imposed by me, but proceed at your own risk, The User (You) are entirely responisble for their actions.

## Training and evaluation data

- [Japanese Common Voice 17](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0)
- [ehehe Corpus](https://huggingface.co/datasets/litagin/ehehe-corpus)
- Manually cleaned and annotated custom Game and Anime dataset (around 8 hours)

## Training procedure

### Training hyperparameters


The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000

### Compute and Duration

- 1x A100(40G)
- 64gb RAM
- BF16
- 14hrs

### Framework versions

- Transformers 4.41.1
- Pytorch 2.4.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1