真快！几分钟就把视频语音识别为文本了，不到10行代码

pip install faster-whisper

from faster_whisper import WhisperModelmodel_size = "large-v3"# Run on GPU with FP16model = WhisperModel(model_size, device="cuda", compute_type="float16")# or run on GPU with INT8# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")# or run on CPU with INT8# model = WhisperModel(model_size, device="cpu", compute_type="int8")segments, info = model.transcribe("audio.mp3", beam_size=5)print("Detected language '%s' with probability %f" % (info.language, info.language_probability))for segment in segments:print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

from flask import Flask, request, jsonifyfrom faster_whisper import WhisperModelapp = Flask(__name__)model_size = "large-v2"model = WhisperModel(model_size, device="cpu", compute_type="int8")@app.route('/transcribe', methods=['POST'])def transcribe():# Get the file path from the requestfile_path = request.json.get('filePath')# Transcribe the filesegments, info = model.transcribe(file_path, beam_size=5, initial_prompt="简体")segments_copy = []with open('segments.txt', 'w') as file:for segment in segments:line = "%.2fs|%.2fs|[%.2fs -> %.2fs]|%s" % (segment.start, segment.end, segment.start, segment.end, segment.text)segments_copy.append(line)file.write(line + '\n')# Prepare the responseresponse_data = {"language": info.language,"language_probability": info.language_probability,"segments": []}for segment in segments_copy:response_data["segments"].append(segment)return jsonify(response_data)if __name__ == '__main__':app.run(debug=False)