def transcribe_audio(file): transcript = openai.audio.transcriptions.create( file=open(audio_test_file, "rb"), model="whisper", ) return transcript.text print(transcribe_audio(audio_test_file)) 在Azure 中使用 Whisper API 的最佳实践。 Whisper API 确实提供了各种参数,可用于更具体的转录。OpenAI ...
def whisper_test(): os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE' filename = "test.mp4" ## window GPU cuda ## window CPU cpu ## mac CPU cpu ## mac GPU model = whisper.load_model("large-v3",device="cuda") result = model.transcribe(audio=filename, fp16 =False) output_directory...
openai.api_type ="azure"openai.api_version ="2023-09-01-preview"model_name ="whisper"deployment_id ="whisper"audio_language="en"audio_test_file ="./wikipediaOcelot.wav"#Azure OpenAI CONFIGURATIONfromopenaiimportAzureOpenAI client = AzureOpenAI( api_key="yourkey", api_version="2023-12-01-pr...
def test_openai_whisper(): # 初始化OpenAI对象 client = OpenAI(base_url="xxx",api_key="xxx") # 打开一个音频文件 audio_file1 = open("demo1.mp3", 'rb') audio_file2 = open("demo2.mp3", 'rb') # 选择模型,并且转录音频的内容 res1 = client.audio.transcriptions.create(model="whisper-...
def whisper_test(): os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE' filename = "test.mp4" ## window GPU cuda ## window CPU cpu ## mac CPU cpu ## mac GPU model = whisper.load_model("large-v3",device="cuda") result = model.transcribe(audio=filename, fp16 =False) ...
audio_test_file = "./wikipediaOcelot.wav"#Azure OpenAI CONFIGURATIONfrom openai import AzureOpenAIclient = AzureOpenAI( api_key="yourkey", api_version="2023-12-01-preview", azure_endpoint = "https://instance.openai.azure.com/" )def transcribe_audio(file): transcript = openai.audio....
audio=AudioSegment.from_file("input.mp3",format="mp3") 1. 请将input.mp3替换为你自己的mp3文件路径。 3. 将音频转为悄悄话 在这一步中,我们将使用pydub库的low_pass_filter方法将音频转为悄悄话。代码如下: whisper_audio=audio.low_pass_filter(500) ...
2. Audio File to Transcribe You will need an audio file that you want to transcribe. The audio file should be in a supported format (.wav). The audio file used for this test is (jfk.wav) Location: Place the models and audio file in the Downloads folderAbout...
curl -X POST -H "content-type: multipart/form-data" -F "initial_prompt="这是一段中文、英文混合的录音,输出请记得加标点符号。"" -F "audio_file=@test.mp3" http://127.0.0.9:9000/asr > test.txt base 模型对短音频的识别效果不错,一般模型越大,识别效果越好。
python infer_ct2.py--audio_path=dataset/test.wav--model_path=models/whisper-tiny-ct2 输出结果如下: {"language":"zh","duration":8.39,"results": [ {"start":0.0,"end":8.39,"text":"近几年不但我用书给女儿压岁也劝说亲朋友不要给女儿压岁钱而改送压岁书"} ],"text":"近几年不但我用...