---
title: wav2vec2-large-xlsr-53-english
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/wav2vec2-large-xlsr-53-english"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/wav2vec2-large-xlsr-53-english.md"
repository: AI-ModelScope/wav2vec2-large-xlsr-53-english
last_updated: 2023-12-27
license: apache-2.0
pipeline_tag: auto-speech-recognition
tasks:
  - auto-speech-recognition
model_type:
  - wav2vec2
architectures:
  - Wav2Vec2ForCTC
parameters: 315.5M
tensor_type:
  - F32
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - Pytorch
language:
  - en
downloads: 2208
stars: 3
tags:
  - audio
  - automatic-speech-recognition
  - en
  - hf-asr-leaderboard
  - mozilla-foundation/common_voice_6_0
  - robust-speech-event
  - speech
  - xlsr-fine-tuning-week
---

# wav2vec2-large-xlsr-53-english

> wav2vec2-large-xlsr-53-english - AI-ModelScope 在 ModelScope 开源的模型。Fine-tuned XLSR-53 large model for speech recognition in English

AI-ModelScope/wav2vec2-large-xlsr-53-english 是 ModelScope 魔搭社区上的 315.5M 参数auto-speech-recognition模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/wav2vec2-large-xlsr-53-english
- **License**: apache-2.0
- **Tasks**: auto-speech-recognition
- **Parameters**: 315.5M
- **Tags**: audio, automatic-speech-recognition, en, hf-asr-leaderboard, mozilla-foundation/common_voice_6_0, robust-speech-event, speech, xlsr-fine-tuning-week
- **Downloads**: 2208
- **Stars**: 3
- **Last updated**: 2023-12-27

Source: https://www.modelscope.cn/models/AI-ModelScope/wav2vec2-large-xlsr-53-english

---

# Fine-tuned XLSR-53 large model for speech recognition in English

Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on English using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice).
When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)

The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

## Usage

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

Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:

```python
from modelscope import snapshot_download
from huggingsound import SpeechRecognitionModel

local_model = snapshot_download("AI-ModelScope/wav2vec2-large-xlsr-53-english",revision='master')
model = SpeechRecognitionModel(local_model)
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)
```

Writing your own inference script:

```python
import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
from modelscope import snapshot_download

LANG_ID = "en"
MODEL_ID = "AI-ModelScope/wav2vec2-large-xlsr-53-english"
SAMPLES = 10

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
local_model = snapshot_download(MODEL_ID,revision='master')
processor = Wav2Vec2Processor.from_pretrained(local_model)
model = Wav2Vec2ForCTC.from_pretrained(local_model)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = batch["sentence"].upper()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits

predicted_ids = torch.argmax(logits, dim=-1)
predicted_sentences = processor.batch_decode(predicted_ids)

for i, predicted_sentence in enumerate(predicted_sentences):
    print("-" * 100)
    print("Reference:", test_dataset[i]["sentence"])
    print("Prediction:", predicted_sentence)
```

| Reference  | Prediction |
| ------------- | ------------- |
| "SHE'LL BE ALL RIGHT." | SHE'LL BE ALL RIGHT |
| SIX | SIX |
| "ALL'S WELL THAT ENDS WELL." | ALL AS WELL THAT ENDS WELL |
| DO YOU MEAN IT? | DO YOU MEAN IT |
| THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE, BUT STILL CAUSES REGRESSIONS. | THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE BUT STILL CAUSES REGRESSION |
| HOW IS MOZILLA GOING TO HANDLE AMBIGUITIES LIKE QUEUE AND CUE? | HOW IS MOSLILLAR GOING TO HANDLE ANDBEWOOTH HIS LIKE Q AND Q |
| "I GUESS YOU MUST THINK I'M KINDA BATTY." | RUSTIAN WASTIN PAN ONTE BATTLY |
| NO ONE NEAR THE REMOTE MACHINE YOU COULD RING? | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING |
| SAUCE FOR THE GOOSE IS SAUCE FOR THE GANDER. | SAUCE FOR THE GUICE IS SAUCE FOR THE GONDER |
| GROVES STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD. | GRAFS STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD |

## Evaluation

1. To evaluate on `mozilla-foundation/common_voice_6_0` with split `test`

```bash
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset mozilla-foundation/common_voice_6_0 --config en --split test
```

2. To evaluate on `speech-recognition-community-v2/dev_data`

```bash
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset speech-recognition-community-v2/dev_data --config en --split validation --chunk_length_s 5.0 --stride_length_s 1.0
```

## Citation
If you want to cite this model you can use this:

```bibtex
@misc{grosman2021xlsr53-large-english,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {E}nglish},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english}},
  year={2021}
}
```