lowhipa-base-asc

This Whisper-for-IPA (WhIPA) model adapter is a PEFT LoRA fine-tuned version of openai/whisper-base on a subset (1k samples) of the Arabic Speech Corpus (https://en.arabicspeechcorpus.com) with custom IPA transcriptions transliterated from the provided Buckwalter transcriptions; ASC-IPA dataset available at https://doi.org/10.5281/zenodo.17111977.

Model description

For deployment and description, please refer to https://github.com/jshrdt/whipa.

from transformers import WhisperForConditionalGeneration, WhisperTokenizer, WhisperProcessor
from peft import PeftModel

tokenizer = WhisperTokenizer.from_pretrained("openai/whisper-base", task="transcribe")
tokenizer.add_special_tokens({"additional_special_tokens": ["<|ip|>"] + tokenizer.all_special_tokens})

base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-base")
base_model.generation_config.lang_to_id["<|ip|>"] = tokenizer.convert_tokens_to_ids(["<|ip|>"])[0]
base_model.resize_token_embeddings(len(tokenizer))

whipa_model = PeftModel.from_pretrained(base_model, "jshrdt/lowhipa-base-asc")

whipa_model.generation_config.language = "<|ip|>"
whipa_model.generation_config.task = "transcribe"

whipa_processor = WhisperProcessor.from_pretrained("openai/whisper-base", task="transcribe")

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5071	2.0	126	0.4070
0.2359	4.0	252	0.2963
0.149	6.0	378	0.2626
0.1051	8.0	504	0.2578
0.0811	10.0	630	0.2584

Framework versions

• PEFT 0.15.1
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• PEFT 0.15.1