vi_whisper-medium
This model is a one shot fine-tuned version of 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:
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
- Downloads last month
- 78
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for DuyTa/vi-whisper-medium-Lora
Base model
openai/whisper-medium