Whisper Base Japanese

🚀 用於語音識別的微調日語Whisper模型

本項目是基於 openai/whisper-base 模型，使用 Common Voice、JVS 和 JSUT 數據集對日語進行微調後的語音識別模型。使用該模型時，請確保輸入的語音採樣率為 16kHz。

🚀 快速開始

本模型可直接按以下方式使用：

from transformers import WhisperForConditionalGeneration, WhisperProcessor
from datasets import load_dataset
import librosa
import torch

LANG_ID = "ja"
MODEL_ID = "Ivydata/whisper-base-japanese"
SAMPLES = 10

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = WhisperProcessor.from_pretrained("openai/whisper-base")
model = WhisperForConditionalGeneration.from_pretrained(MODEL_ID)
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(
    language="ja", task="transcribe"
)
model.config.suppress_tokens = []

# 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()
    batch["sampling_rate"] = sampling_rate
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
sample = test_dataset[0]
input_features = processor(sample["speech"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
predicted_ids = model.generate(input_features)

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
# ['<|startoftranscript|><|ja|><|transcribe|><|notimestamps|>木村さんに電話を貸してもらいました。<|endoftext|>']

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
# ['木村さんに電話を貸してもらいました。']

💻 使用示例

基礎用法

from transformers import WhisperForConditionalGeneration, WhisperProcessor
from datasets import load_dataset
import librosa
import torch

LANG_ID = "ja"
MODEL_ID = "Ivydata/whisper-base-japanese"
SAMPLES = 10

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = WhisperProcessor.from_pretrained("openai/whisper-base")
model = WhisperForConditionalGeneration.from_pretrained(MODEL_ID)
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(
    language="ja", task="transcribe"
)
model.config.suppress_tokens = []

# 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()
    batch["sampling_rate"] = sampling_rate
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
sample = test_dataset[0]
input_features = processor(sample["speech"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
predicted_ids = model.generate(input_features)

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
# ['<|startoftranscript|><|ja|><|transcribe|><|notimestamps|>木村さんに電話を貸してもらいました。<|endoftext|>']

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
# ['木村さんに電話を貸してもらいました。']

📚 詳細文檔

測試結果

以下表格展示了模型在 TEDxJP-10K 數據集上測試的字符錯誤率（CER）：

📄 許可證

本項目採用 Apache-2.0 許可證。