Skip to main content

Monotonic Alignment Search

Project description

EveryVoiceTTS fork of monotonic_align

We forked https://github.com/resemble-ai/monotonic_align in order to publish it to PyPI so that it can be installed without requiring a clone:

pip install ilt-monotonic-align

Original README file from resemble-ai:

Adapted from the MAS in Glow-TTS. I made it installable and added variants.

Installation

pip install git+https://github.com/resemble-ai/monotonic_align.git

Installing monotonic_align doesn't require torch, but using monotonic_align will. Please install PyTorch yourself, as its installation differ from system to system.

How to Use

# Suppose you have:
# 1. a probability matrix of size (batch_size=B, symbol_len=S, mel_lens=T)
#    NOTE: a similarity matrix (a higher score means better) or negative cost will do
#          but may have issues.
# 2. an array of symbol lengths `symbol_lens` of size (batch_size=B)
# 3. an array of mel-spectrogram lengths `mel_lens` of size (batch_size=B)

from monotonic_align import mask_from_lens, maximum_path
mask_ST = mask_from_lens(similarity, symbol_lens, mel_lens)
alignment = maximum_path(similarity, mask_ST)  # (B, S, T)

# NOTE:
# - If `mask` is not specified, the default mask is `True` for all elements.
# - You can specify `topology` if you want to use other variants of alignment algorithms.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ilt_monotonic_align-1.2.1.tar.gz (606.7 kB view details)

Uploaded Source

File details

Details for the file ilt_monotonic_align-1.2.1.tar.gz.

File metadata

  • Download URL: ilt_monotonic_align-1.2.1.tar.gz
  • Upload date:
  • Size: 606.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for ilt_monotonic_align-1.2.1.tar.gz
Algorithm Hash digest
SHA256 db7b5cfb8be76a24655ff75484fae3f8819370f1ab5184e9e64d0681906549e4
MD5 ad3a6048b8950f0bc1cfde85a21bf9c3
BLAKE2b-256 f6bb6226f2f506b8f05f670d440c87e212d1eeba0b16e76cf806822bf2542389

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page