wav2vec2-large-xlsr-53-icelandic-ep30-967h

The "wav2vec2-large-xlsr-53-icelandic-ep30-967h" is an acoustic model suitable for Automatic Speech Recognition in Icelandic. It is the result of fine-tuning the model [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) for 30 epochs with 967 hours of Icelandic data collected by the [Language and Voice Laboratory](https://huggingface.co/language-and-voice-lab) through the platform [Samrómur](https://samromur.is/). The specific data that was used to fine-tune the model is the corpus [Samrómur Milljón](https://huggingface.co/datasets/language-and-voice-lab/samromur_milljon), which is the result of the automatic verification of 1 million of recordings comming from the corpus ["Samromur Unverified 22.07"](http://hdl.handle.net/20.500.12537/265). It has to be pointed out that this model was trained with different data than our previous model [ wav2vec2-large-xlsr-53-icelandic-ep10-1000h ](https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h). The fine-tuning process was performed during July (2023) in the servers of the Language and Voice Laboratory (https://lvl.ru.is/) at Reykjavík University (Iceland) by [Carlos Daniel Hernández Mena](https://huggingface.co/carlosdanielhernandezmena). import torch from transformers import Wav2Vec2Processor from transformers import Wav2Vec2ForCTC MODEL_NAME="language-and-voice-lab/wav2vec2-large-xlsr-53-icelandic-ep30-967h" processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME) model = Wav2Vec2ForCTC.from_pretrained(MODEL_NAME) from datasets import load_dataset, load_metric, Audio ds=load_dataset("language-and-voice-lab/samromur_children", split="test") ds = ds.cast_column("audio", Audio(sampling_rate=16_000)) def prepare_dataset(batch): audio = batch["audio"] batch["input_values"] = processor(audio["array"], sampling_rate=audio["sampling_rate"]).input_values[0] with processor.as_target_processor(): batch["labels"] = processor(batch["normalized_text"]).input_ids return batch ds = ds.map(prepare_dataset, remove_columns=ds.column_names,num_proc=1) import numpy as np wer_metric = load_metric("wer") def compute_metrics(pred): pred_logits = pred.predictions pred_ids = np.argmax(pred_logits, axis=-1) pred.label_ids[pred.label_ids == -100] = processor.tokenizer.pad_token_id pred_str = processor.batch_decode(pred_ids) label_str = processor.batch_decode(pred.label_ids, group_tokens=False) wer = wer_metric.compute(predictions=pred_str, references=label_str) return {"wer": wer} model = model.to(torch.device("cuda")) def map_to_result(batch): with torch.no_grad(): input_values = torch.tensor(batch["input_values"], device="cuda").unsqueeze(0) logits = model(input_values).logits pred_ids = torch.argmax(logits, dim=-1) batch["pred_str"] = processor.batch_decode(pred_ids)[0] batch["sentence"] = processor.decode(batch["labels"], group_tokens=False) return batch results = ds.map(map_to_result,remove_columns=ds.column_names) print("Test WER: {:.3f}".format(wer_metric.compute(predictions=results["pred_str"], references=results["sentence"]))) **Test Result**: 0.076 *When publishing results based on these models please refer to:* @inproceedings{mena2024samromur, title={Samr{\'o}mur Millj{\'o}n: An ASR Corpus of One Million Verified Read Prompts in Icelandic}, author={Mena, Carlos Daniel Hernandez and Gunnarsson, {\TH}orsteinn Da{\dh}i and Gu{\dh}nason, J{\'o}n}, booktitle={Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)}, pages={14305--14312}, year={2024} } @misc{mena2023xlrs53icelandic30ep967h, title={Acoustic Model in Icelandic: wav2vec2-large-xlsr-53-icelandic-ep30-967h.}, author={Hernandez Mena, Carlos Daniel}, url={https://huggingface.co/language-and-voice-lab/wav2vec2-large-xlsr-53-icelandic-ep30-967h}, year={2023} } --> Thanks to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make this model possible. We also want to thank to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture. This model is an unexpected result of all the resources gathered by the Programme. Special thanks to Björn Ingi Stefánsson for setting up the configuration of the server where this model was trained.