1
---
2
language: en
3
datasets:
4
- common_voice
5
metrics:
6
- wer
7
- cer
8
tags:
9
- audio
10
- automatic-speech-recognition
11
- speech
12
- xlsr-fine-tuning-week
13
license: apache-2.0
14
model-index:
15
- name: XLSR Wav2Vec2 English by Jonatas Grosman
16
  results:
17
  - task: 
18
      name: Speech Recognition
19
      type: automatic-speech-recognition
20
    dataset:
21
      name: Common Voice en
22
      type: common_voice
23
      args: en
24
    metrics:
25
       - name: Test WER
26
         type: wer
27
         value: 18.98
28
       - name: Test CER
29
         type: cer
30
         value: 8.29
31
---
32
33
# Wav2Vec2-Large-XLSR-53-English
34
35
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on English using the [Common Voice](https://huggingface.co/datasets/common_voice).
36
When using this model, make sure that your speech input is sampled at 16kHz.
37
38
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/) :)
39
40
The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
41
42
## Usage
43
44
The model can be used directly (without a language model) as follows...
45
46
Using the [ASRecognition](https://github.com/jonatasgrosman/asrecognition) library:
47
48
```python
49
from asrecognition import ASREngine
50
51
asr = ASREngine("en", model_path="jonatasgrosman/wav2vec2-large-xlsr-53-english")
52
53
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
54
transcriptions = asr.transcribe(audio_paths)
55
```
56
57
Writing your own inference script:
58
59
```python
60
import torch
61
import librosa
62
from datasets import load_dataset
63
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
64
65
LANG_ID = "en"
66
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-english"
67
SAMPLES = 10
68
69
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
70
71
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
72
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
73
74
# Preprocessing the datasets.
75
# We need to read the audio files as arrays
76
def speech_file_to_array_fn(batch):
77
    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
78
    batch["speech"] = speech_array
79
    batch["sentence"] = batch["sentence"].upper()
80
    return batch
81
82
test_dataset = test_dataset.map(speech_file_to_array_fn)
83
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
84
85
with torch.no_grad():
86
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
87
88
predicted_ids = torch.argmax(logits, dim=-1)
89
predicted_sentences = processor.batch_decode(predicted_ids)
90
91
for i, predicted_sentence in enumerate(predicted_sentences):
92
    print("-" * 100)
93
    print("Reference:", test_dataset[i]["sentence"])
94
    print("Prediction:", predicted_sentence)
95
```
96
97
| Reference  | Prediction |
98
| ------------- | ------------- |
99
| "SHE'LL BE ALL RIGHT." | SHE'LL BE ALL RIGHT |
100
| SIX | SIX |
101
| "ALL'S WELL THAT ENDS WELL." | ALL AS WELL THAT ENDS WELL |
102
| DO YOU MEAN IT? | DO YOU MEAN IT |
103
| 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 |
104
| HOW IS MOZILLA GOING TO HANDLE AMBIGUITIES LIKE QUEUE AND CUE? | HOW IS MOSLILLAR GOING TO HANDLE ANDBEWOOTH HIS LIKE Q AND Q |
105
| "I GUESS YOU MUST THINK I'M KINDA BATTY." | RUSTIAN WASTIN PAN ONTE BATTLY |
106
| NO ONE NEAR THE REMOTE MACHINE YOU COULD RING? | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING |
107
| SAUCE FOR THE GOOSE IS SAUCE FOR THE GANDER. | SAUCE FOR THE GUICE IS SAUCE FOR THE GONDER |
108
| GROVES STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD. | GRAFS STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD |
109
110
## Evaluation
111
112
The model can be evaluated as follows on the English test data of Common Voice.
113
114
```python
115
import torch
116
import re
117
import librosa
118
from datasets import load_dataset, load_metric
119
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
120
121
LANG_ID = "en"
122
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-english"
123
DEVICE = "cuda"
124
125
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
126
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
127
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
128
                   "、", "﹂", "﹁", "‧", "~", "﹏", ",", "{", "}", "(", ")", "[", "]", "【", "】", "‥", "〽",
129
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", ":", "!", "?", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]
130
131
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
132
133
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
134
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
135
136
chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"
137
138
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
139
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
140
model.to(DEVICE)
141
142
# Preprocessing the datasets.
143
# We need to read the audio files as arrays
144
def speech_file_to_array_fn(batch):
145
    with warnings.catch_warnings():
146
        warnings.simplefilter("ignore")
147
        speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
148
    batch["speech"] = speech_array
149
    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
150
    return batch
151
152
test_dataset = test_dataset.map(speech_file_to_array_fn)
153
154
# Preprocessing the datasets.
155
# We need to read the audio files as arrays
156
def evaluate(batch):
157
    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
158
159
    with torch.no_grad():
160
        logits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits
161
162
    pred_ids = torch.argmax(logits, dim=-1)
163
    batch["pred_strings"] = processor.batch_decode(pred_ids)
164
    return batch
165
166
result = test_dataset.map(evaluate, batched=True, batch_size=8)
167
168
predictions = [x.upper() for x in result["pred_strings"]]
169
references = [x.upper() for x in result["sentence"]]
170
171
print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
172
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
173
```
174
175
**Test Result**:
176
177
In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-06-17). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.
178
179
| Model | WER | CER |
180
| ------------- | ------------- | ------------- |
181
| jonatasgrosman/wav2vec2-large-xlsr-53-english | **18.98%** | **8.29%** |
182
| jonatasgrosman/wav2vec2-large-english | 21.53% | 9.66% |
183
| facebook/wav2vec2-large-960h-lv60-self | 22.03% | 10.39% |
184
| facebook/wav2vec2-large-960h-lv60 | 23.97% | 11.14% |
185
| boris/xlsr-en-punctuation | 29.10% | 10.75% |
186
| facebook/wav2vec2-large-960h | 32.79% | 16.03% |
187
| facebook/wav2vec2-base-960h | 39.86% | 19.89% |
188
| facebook/wav2vec2-base-100h | 51.06% | 25.06% |
189
| elgeish/wav2vec2-large-lv60-timit-asr | 59.96% | 34.28% |
190
| facebook/wav2vec2-base-10k-voxpopuli-ft-en | 66.41% | 36.76% |
191
| elgeish/wav2vec2-base-timit-asr | 68.78% | 36.81% |
192