diff --git a/README.md b/README.md index fedacb2da5ec2affbeb5c295a7ad81fa51cc0713..6ad49ced1d0fdd51d0d8153e59426e95261e996c 100644 --- a/README.md +++ b/README.md @@ -9,6 +9,6 @@ Use docker to build and run image: ``` docker build -t <name> . -docker run <name> -v "/samba:/samba" +docker run -v /samba:/samba <name> ``` diff --git a/src/predict_lang.py b/src/predict_lang.py index ef03443f316f0490c4fc6dcf8c0ff644b964c12c..99c319ac894459a22457b4c9fde39c60e9e270b3 100644 --- a/src/predict_lang.py +++ b/src/predict_lang.py @@ -1,18 +1,17 @@ import fasttext import nlp_ws - class PredictLangWorker(nlp_ws.NLPWorker): - + def __init__(self): self.model = fasttext.load_model("lid.176.bin") - def process(self, input_file: str, - task_options: dict, - output_file: str) -> None: + def process(self, input_file: str, task_options: dict, output_file: str) -> None: with open(input_file, "r") as f: - text = f.read().replace('\n', ' ') + text = f.read().replace('\n',' ') + print(text) predict = self.model.predict(text)[0][0] with open(output_file, "w") as f: - f.write(predict) - return self.model.predict(str(text)) + f.write(text+ predict) + print(predict) + return predict