Modelpublic

jshrdt/lowhipa-base-cv

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes72downloads

Model Card

lowhipa-base-cv

This Whisper-for-IPA (WhIPA) model adapter is a PEFT LoRA fine-tuned version of openai/whisper-base on a subset of the CommonVoice11 dataset (1k samples each from Greek, Finnish, Hungarian, Japanese, Maltese, Polish, Tamil) with G2P-based IPA transcriptions.

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-cv")

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

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

jshrdt/lowhipa-base-cv

lowhipa-base-cv

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions