---
library_name: peft
license: apache-2.0
datasets:
- google/fleurs
language:
- hi
---

I implement  a method called PEFT (Parameter Efficient Fine-Tuning) for finetuning whisperlarge v2 model on google-fleurs voice data for transcription task.


## 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
### Framework versions


- PEFT 0.4.0.dev0