Xlsr Wav2vec English
基於facebook/wav2vec2-large在通用語音數據集上進行英語微調的自動語音識別模型,支持16kHz採樣率的語音輸入。
下載量 27
發布時間 : 3/2/2022
模型概述
這是一個用於英語自動語音識別(ASR)的Wav2Vec2模型,經過微調後可直接使用,無需額外語言模型。
模型特點
高精度識別
在通用語音英語測試集上達到21.53%的詞錯誤率和9.66%的字符錯誤率
無需語言模型
可直接使用,無需額外語言模型支持
16kHz採樣率支持
專門針對16kHz採樣率的語音輸入進行優化
模型能力
英語語音識別
音頻轉錄
自動語音轉文本
使用案例
語音轉錄
會議記錄
將會議錄音自動轉錄為文字記錄
播客轉文字
將英語播客內容自動轉換為文字稿
輔助技術
語音控制
為應用程序添加語音控制功能
🚀 Wav2vec2-Large-English
Wav2vec2-Large-English 是基於 Common Voice 英文數據集對 facebook/wav2vec2-large 進行微調得到的模型。使用此模型時,請確保語音輸入的採樣率為 16kHz。
🚀 快速開始
本模型可直接使用(無需語言模型),以下是具體使用方法。
✨ 主要特性
- 數據集:使用 Common Voice 英文數據集進行微調。
- 評估指標:支持字錯誤率(WER)和字符錯誤率(CER)評估。
📦 安裝指南
文檔未提及安裝步驟,故跳過此章節。
💻 使用示例
基礎用法
使用 ASRecognition 庫:
from asrecognition import ASREngine
asr = ASREngine("fr", model_path="jonatasgrosman/wav2vec2-large-english")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
transcriptions = asr.transcribe(audio_paths)
高級用法
編寫自己的推理腳本:
import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-english"
SAMPLES = 10
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
# 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)
以下是預測結果示例:
參考文本 | 預測文本 |
---|---|
"SHE'LL BE ALL RIGHT." | SHELL BE ALL RIGHT |
SIX | SIX |
"ALL'S WELL THAT ENDS WELL." | ALLAS WELL THAT ENDS WELL |
DO YOU MEAN IT? | W 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 REGRESTION |
HOW IS MOZILLA GOING TO HANDLE AMBIGUITIES LIKE QUEUE AND CUE? | HOW IS MOSILLA GOING TO BANDL AND BE WHIT IS LIKE QU AND QU |
"I GUESS YOU MUST THINK I'M KINDA BATTY." | RUSTION AS HAME AK AN THE POT |
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 GUCE 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 |
📚 詳細文檔
評估方法
本模型可在 Common Voice 英文測試數據上進行評估,以下是評估代碼:
import torch
import re
import librosa
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-english"
DEVICE = "cuda"
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
"؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
"{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
"、", "﹂", "﹁", "‧", "~", "﹏", ",", "{", "}", "(", ")", "[", "]", "【", "】", "‥", "〽",
"『", "』", "〝", "〟", "⟨", "⟩", "〜", ":", "!", "?", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
model.to(DEVICE)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]
print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
測試結果
以下表格展示了本模型及其他模型的字錯誤率(WER)和字符錯誤率(CER)。需要注意的是,表格中的結果可能與其他評估腳本的結果不同,這可能是由於使用的評估腳本存在差異。
模型 | 字錯誤率(WER) | 字符錯誤率(CER) |
---|---|---|
wav2vec2-large-xlsr-53-english | 18.98% | 8.29% |
wav2vec2-large-xlsr-53-greek | 18.99% | 10.60% |
wav2vec2-large-xlsr-53-hindi | 20.01% | 9.66% |
wav2vec2-large-960h-lv60-english | 22.03% | 10.39% |
wav2vec2-base-100h-lv60-english | 24.97% | 11.14% |
📄 許可證
本模型使用 Apache-2.0 許可證。
Voice Activity Detection
MIT
基於pyannote.audio 2.1版本的語音活動檢測模型,用於識別音頻中的語音活動時間段
語音識別
V
pyannote
7.7M
181
Wav2vec2 Large Xlsr 53 Portuguese
Apache-2.0
這是一個針對葡萄牙語語音識別任務微調的XLSR-53大模型,基於Common Voice 6.1數據集訓練,支持葡萄牙語語音轉文本。
語音識別 其他
W
jonatasgrosman
4.9M
32
Whisper Large V3
Apache-2.0
Whisper是由OpenAI提出的先進自動語音識別(ASR)和語音翻譯模型,在超過500萬小時的標註數據上訓練,具有強大的跨數據集和跨領域泛化能力。
語音識別 支持多種語言
W
openai
4.6M
4,321
Whisper Large V3 Turbo
MIT
Whisper是由OpenAI開發的最先進的自動語音識別(ASR)和語音翻譯模型,經過超過500萬小時標記數據的訓練,在零樣本設置下展現出強大的泛化能力。
語音識別
Transformers 支持多種語言

W
openai
4.0M
2,317
Wav2vec2 Large Xlsr 53 Russian
Apache-2.0
基於facebook/wav2vec2-large-xlsr-53模型微調的俄語語音識別模型,支持16kHz採樣率的語音輸入
語音識別 其他
W
jonatasgrosman
3.9M
54
Wav2vec2 Large Xlsr 53 Chinese Zh Cn
Apache-2.0
基於facebook/wav2vec2-large-xlsr-53模型微調的中文語音識別模型,支持16kHz採樣率的語音輸入。
語音識別 中文
W
jonatasgrosman
3.8M
110
Wav2vec2 Large Xlsr 53 Dutch
Apache-2.0
基於facebook/wav2vec2-large-xlsr-53微調的荷蘭語語音識別模型,在Common Voice和CSS10數據集上訓練,支持16kHz音頻輸入。
語音識別 其他
W
jonatasgrosman
3.0M
12
Wav2vec2 Large Xlsr 53 Japanese
Apache-2.0
基於facebook/wav2vec2-large-xlsr-53模型微調的日語語音識別模型,支持16kHz採樣率的語音輸入
語音識別 日語
W
jonatasgrosman
2.9M
33
Mms 300m 1130 Forced Aligner
基於Hugging Face預訓練模型的文本與音頻強制對齊工具,支持多種語言,內存效率高
語音識別
Transformers 支持多種語言

M
MahmoudAshraf
2.5M
50
Wav2vec2 Large Xlsr 53 Arabic
Apache-2.0
基於facebook/wav2vec2-large-xlsr-53微調的阿拉伯語語音識別模型,在Common Voice和阿拉伯語語音語料庫上訓練
語音識別 阿拉伯語
W
jonatasgrosman
2.3M
37
精選推薦AI模型
Llama 3 Typhoon V1.5x 8b Instruct
專為泰語設計的80億參數指令模型,性能媲美GPT-3.5-turbo,優化了應用場景、檢索增強生成、受限生成和推理任務
大型語言模型
Transformers 支持多種語言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一個基於SODA數據集訓練的超小型對話模型,專為邊緣設備推理設計,體積僅為Cosmo-3B模型的2%左右。
對話系統
Transformers 英語

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基於RoBERTa架構的中文抽取式問答模型,適用於從給定文本中提取答案的任務。
問答系統 中文
R
uer
2,694
98