Error as e: raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e return process, None import streamlink import subprocess import threading stream_options = streamlink.streams(stream) if not stream_options: print("No playable streams found on this URL:", stream) sys....
File "/home/rootroot/.local/lib/python3.8/site-packages/whisper/audio.py", line 140, in log_mel_spectrogram audio = load_audio(audio) File "/home/rootroot/.local/lib/python3.8/site-packages/whisper/audio.py", line 60, in load_audio raise RuntimeError(f"Failed to load audio: {e.std...
capture_stdout=True, capture_stderr=True) ) except ffmpeg.Error as e: raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0
("-",format="s16le",acodec="pcm_s16le",ac=1,ar=sample_rate) .run(cmd=["ffmpeg","-nostdin"],capture_stdout=True,capture_stderr=True) )exceptffmpeg.Errorase:raiseRuntimeError(f"Failed to load audio:{e.stderr.decode()}")fromearr=np.frombuffer(y,np.int16).flatten().astype(np....
raise Exception('Failed to download video') return f'audio/{video_id}.m4a' def process(youtube_url, language): video_id = extract_video_id(youtube_url) if not video_id: st.error("Invalid YouTube URL") return try: progress_text = "Downloading video..." ...
model=whisper.load_model("base")result=model.transcribe("audio.mp3")print(result["text"]) 精细化使用: 代码语言:shell 复制 importwhisper model=whisper.load_model("base")# load audio and pad/trim it to fit 30 secondsaudio=whisper.load_audio("audio.mp3")audio=whisper.pad_or_trim(audio)# ...
import whisper model = whisper.load_model("base") result = model.transcribe("audio.mp3") print(result["text"]) 精细化使用: import whisper model = whisper.load_model("base") # load audio and pad/trim it to fit 30 seconds audio = whisper.load_audio("audio.mp3") audio = whisper.pad_...
result = model.transcribe("audio.mp3") print(result["text"]) 1. 2. 3. 4. 5. 精细化使用: import whisper model = whisper.load_model("base") # load audio and pad/trim it to fit 30 seconds audio = whisper.load_audio("audio.mp3") ...
load_model("base") result = model.transcribe("audio.mp3") print(result["text"]) 使用体验 安装whisper后,可以根据以上说明直接命令行执行,会自动下载指定的模型: 这里我是转换一个视频,会自动生成字幕格式的,使用非常方便: 除了直接识别语音生成文字和视频字幕,还可以直接转换中文为英文: 直接把中文视频生成...
可以看到代码中是将sdl_audio_callback赋值给了wanted_spec.callback,这个函数位于ff_ffplay.c中。opaque赋值给了userdata,是因为opaque的结构体类型是FFPlayer,里面包含了输入和输出buffer。 下面看一下while循环的SDL_AoutOpenAudio是怎么做的: int SDL_AoutOpenAudio(SDL_Aout *aout, const SDL_AudioSpec *desired,...