21 lines
691 B
Python
21 lines
691 B
Python
|
from faster_whisper import WhisperModel
|
||
|
|
|
||
|
|
model_size = "turbo"
|
||
|
|
|
||
|
|
# Run on GPU with FP16
|
||
|
|
model = 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, language="zh", initial_prompt="这是一段小说。")
|
||
|
|
|
||
|
|
print(info)
|
||
|
|
|
||
|
|
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))
|