---
license: cc-by-4.0
language:
- qu
metrics:
- cer
pipeline_tag: automatic-speech-recognition
datasets:
- ivangtorre/second_americas_nlp_2022
tags:
- audio
- automatic-speech-recognition
- speech
- qu
- xlsr-fine-tuning
model-index:
- name: Wav2Vec2 XLSR 300M Quechua Model by M Romero and Ivan G Torre
  results:
  - task:
      name: Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Americas NLP 2022 qu
      type: second_americas_nlp_2022
      args: qu
    metrics:
    - name: Test CER
      type: cer
      value: 16.02

---

This model was finetuned from a Wav2vec2.0 XLS-R model: 300M with the Quechua train parition of the Americas NLP 2022 dataset. This challenge took place during NeurIPSS 2022.



## Example of usage

The model can be used directly (without a language model) as follows:

```python
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
import torch
import torchaudio

# load model and processor
processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")

# Pat to wav file
pathfile = "/path/to/wavfile"

# Load and normalize the file
wav, curr_sample_rate = sf.read(pathfile, dtype="float32")
feats = torch.from_numpy(wav).float()
with torch.no_grad():
    feats = F.layer_norm(feats, feats.shape)
feats = torch.unsqueeze(feats, 0)
logits = model(feats).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
print("HF prediction: ", transcription)
```


This code snipnet shows how to Evaluate the wav2vec2-xlsr-300m-quechua in [Second Americas NLP 2022 Quechua dev set](https://huggingface.co/datasets/ivangtorre/second_americas_nlp_2022)

```python
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
from jiwer import cer
import torch.nn.functional as F


librispeech_eval = load_dataset("ivangtorre/second_americas_nlp_2022", split="validation")

model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")

def map_to_pred(batch):
    wav = batch["audio"][0]["array"]
    feats = torch.from_numpy(wav).float()
    feats = F.layer_norm(feats, feats.shape) # Normalization performed during finetuning
    feats = torch.unsqueeze(feats, 0)
    logits = model(feats).logits
    predicted_ids = torch.argmax(logits, dim=-1)
    batch["transcription"] = processor.batch_decode(predicted_ids)
    return batch

result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1)

print("CER:", cer(result["source_processed"], result["transcription"]))
```

## Citation

```bibtex
@misc{grosman2021xlsr-1b-russian,
  title={Fine-tuned {XLS-R} 1{B} model for speech recognition in {R}ussian},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-russian}},
  year={2022}
}
```