Fixing widget error and bibtex format

3ca9037 7 months ago

No virus

7.29 kB

	---
	language: is
	datasets:
	- language-and-voice-lab/samromur_milljon
	tags:
	- audio
	- automatic-speech-recognition
	- icelandic
	- xlrs-53-icelandic
	- iceland
	- reykjavik
	- samromur
	license: cc-by-4.0
	model-index:
	- name: wav2vec2-large-xlsr-53-icelandic-ep30-967h
	results:
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Samrómur (Test)
	type: language-and-voice-lab/samromur_asr
	split: test
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 7.698
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Samrómur (Dev)
	type: language-and-voice-lab/samromur_asr
	split: validation
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 6.786
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Samrómur Children (Test)
	type: language-and-voice-lab/samromur_children
	split: test
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 6.467
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Samrómur Children (Dev)
	type: language-and-voice-lab/samromur_children
	split: validation
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 4.234
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Malrómur (Test)
	type: language-and-voice-lab/malromur_asr
	split: test
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 6.631
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Malrómur (Dev)
	type: language-and-voice-lab/malromur_asr
	split: validation
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 5.836
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Althingi (Test)
	type: language-and-voice-lab/althingi_asr
	split: test
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 17.904
	- task:
	name: Automatic Speech Recognition
	type: automatic-speech-recognition
	dataset:
	name: Althingi (Dev)
	type: language-and-voice-lab/althingi_asr
	split: validation
	args:
	language: is
	metrics:
	- name: WER
	type: wer
	value: 17.931
	---
	# 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).

	# Evaluation
	```python
	import torch
	from transformers import Wav2Vec2Processor
	from transformers import Wav2Vec2ForCTC

	#Load the processor and model.
	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)

	#Load the dataset
	from datasets import load_dataset, load_metric, Audio
	ds=load_dataset("language-and-voice-lab/samromur_children", split="test")

	#Downsample to 16kHz
	ds = ds.cast_column("audio", Audio(sampling_rate=16_000))

	#Process the dataset
	def prepare_dataset(batch):
	audio = batch["audio"]
	#Batched output is "un-batched" to ensure mapping is correct
	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)

	#Define the evaluation metric
	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)
	#We do not want to group tokens when computing the metrics
	label_str = processor.batch_decode(pred.label_ids, group_tokens=False)
	wer = wer_metric.compute(predictions=pred_str, references=label_str)
	return {"wer": wer}

	#Do the evaluation (with batch_size=1)
	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)

	#Compute the overall WER now.
	print("Test WER: {:.3f}".format(wer_metric.compute(predictions=results["pred_str"], references=results["sentence"])))
	```
	Test Result: 0.076

	# BibTeX entry and citation info
	When publishing results based on these models please refer to:
	```bibtex
	@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}
	}
	```

	# Acknowledgements

	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.