SOTA Open Source TTS
import io
import struct
import wave
from dataclasses import dataclass
from typing import Literal, Optional, Tuple
import numpy as np
@dataclass
class InferenceResult:
code: Literal["header", "segment", "error", "final"]
audio: Optional[Tuple[int, np.ndarray]]
error: Optional[Exception]
def wav_chunk_header(
sample_rate: int = 44100, bit_depth: int = 16, channels: int = 1
) -> bytes:
"""The 44-byte header of a WAV stream whose length is not known yet.
The RIFF and data sizes are 0xFFFFFFFF, which readers take as "until the end
of the stream"; with 0, some (libsndfile) read no audio at all.
"""
buffer = io.BytesIO()
with wave.open(buffer, "wb") as wav_file:
wav_file.setnchannels(channels)
wav_file.setsampwidth(bit_depth // 8)
wav_file.setframerate(sample_rate)
header = buffer.getvalue()
buffer.close()
unknown = struct.pack("<I", 0xFFFFFFFF)
return header[:4] + unknown + header[8:40] + unknown