RMSnow's picture
add backend inference and inferface output
0883aa1
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
# This module is modified from [Whisper](https://github.com/openai/whisper.git).
# ## Citations
# ```bibtex
# @inproceedings{openai-whisper,
# author = {Alec Radford and
# Jong Wook Kim and
# Tao Xu and
# Greg Brockman and
# Christine McLeavey and
# Ilya Sutskever},
# title = {Robust Speech Recognition via Large-Scale Weak Supervision},
# booktitle = {{ICML}},
# series = {Proceedings of Machine Learning Research},
# volume = {202},
# pages = {28492--28518},
# publisher = {{PMLR}},
# year = {2023}
# }
# ```
#
import zlib
from typing import Iterator, TextIO
def exact_div(x, y):
assert x % y == 0
return x // y
def str2bool(string):
str2val = {"True": True, "False": False}
if string in str2val:
return str2val[string]
else:
raise ValueError(f"Expected one of {set(str2val.keys())}, got {string}")
def optional_int(string):
return None if string == "None" else int(string)
def optional_float(string):
return None if string == "None" else float(string)
def compression_ratio(text) -> float:
text_bytes = text.encode("utf-8")
return len(text_bytes) / len(zlib.compress(text_bytes))
def format_timestamp(
seconds: float, always_include_hours: bool = False, decimal_marker: str = "."
):
assert seconds >= 0, "non-negative timestamp expected"
milliseconds = round(seconds * 1000.0)
hours = milliseconds // 3_600_000
milliseconds -= hours * 3_600_000
minutes = milliseconds // 60_000
milliseconds -= minutes * 60_000
seconds = milliseconds // 1_000
milliseconds -= seconds * 1_000
hours_marker = f"{hours:02d}:" if always_include_hours or hours > 0 else ""
return (
f"{hours_marker}{minutes:02d}:{seconds:02d}{decimal_marker}{milliseconds:03d}"
)
def write_txt(transcript: Iterator[dict], file: TextIO):
for segment in transcript:
print(segment["text"].strip(), file=file, flush=True)
def write_vtt(transcript: Iterator[dict], file: TextIO):
print("WEBVTT\n", file=file)
for segment in transcript:
print(
f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
f"{segment['text'].strip().replace('-->', '->')}\n",
file=file,
flush=True,
)
def write_srt(transcript: Iterator[dict], file: TextIO):
"""
Write a transcript to a file in SRT format.
Example usage:
from pathlib import Path
from whisper.utils import write_srt
result = transcribe(model, audio_path, temperature=temperature, **args)
# save SRT
audio_basename = Path(audio_path).stem
with open(Path(output_dir) / (audio_basename + ".srt"), "w", encoding="utf-8") as srt:
write_srt(result["segments"], file=srt)
"""
for i, segment in enumerate(transcript, start=1):
# write srt lines
print(
f"{i}\n"
f"{format_timestamp(segment['start'], always_include_hours=True, decimal_marker=',')} --> "
f"{format_timestamp(segment['end'], always_include_hours=True, decimal_marker=',')}\n"
f"{segment['text'].strip().replace('-->', '->')}\n",
file=file,
flush=True,
)