Spaces:
Sleeping
Sleeping
| import ffmpeg | |
| import numpy as np | |
| # import whisper | |
| # model = whisper.load_model("base") | |
| def load_audio(file: (str, bytes), sr: int = 16000): | |
| """ | |
| Open an audio file and read as mono waveform, resampling as necessary | |
| Parameters | |
| ---------- | |
| file: (str, bytes) | |
| The audio file to open or bytes of audio file | |
| sr: int | |
| The sample rate to resample the audio if necessary | |
| Returns | |
| ------- | |
| A NumPy array containing the audio waveform, in float32 dtype. | |
| """ | |
| if isinstance(file, bytes): | |
| inp = file | |
| file = 'pipe:' | |
| else: | |
| inp = None | |
| try: | |
| out, _ = ( | |
| ffmpeg.input(file, threads=0) | |
| .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr) | |
| .run(cmd="ffmpeg", capture_stdout=True, capture_stderr=True, input=inp) | |
| ) | |
| 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 | |
| def stt_client(audio_data): | |
| return "" | |
| # audio = whisper.pad_or_trim(load_audio(audio_data)) | |
| # mel = whisper.log_mel_spectrogram(audio).to(model.device) | |
| # options = whisper.DecodingOptions(fp16=False) | |
| # result = whisper.decode(model, mel, options) | |
| # return ""result.text | |