---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer , Lora adapter implement
metrics:
- wer
model-index:
- name: vi_whisper-small
  results:

  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: vin100h
      type: vin
      config: Cleaned
      split: Train 0.8 , Test 0.2
    metrics:
    - name: Wer
      type: wer
      value: 21.68
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# vi_whisper-medium

This model is a one shot fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Vin100h dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2894 
- Wer: 21.68 on whisper-quantized model by CTranslate2
- 


# Model description

To use quantized model , firstly , read the doc of how to use CTranslate2 converter and Faster Whisper repo in here:
- [CTranslate2](https://github.com/OpenNMT/CTranslate2.git)
- [Faster-Whipser](https://github.com/guillaumekln/faster-whisper)


## Intended uses & limitations

More information needed

## Training and evaluation data



## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- 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: 1000
- training_steps: 8000

### Framework versions

- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu11.8
- Datasets 2.13.1
- Tokenizers 0.13.3
- PEFT 0.5.0.dev0
## Training procedure


The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32