Skip to main content

custom-rnn

A lightweight, NumPy-only neural network library implementing recurrent architectures and CTC (Connectionist Temporal Classification) from scratch.

Features

  • RNN Cell — vanilla recurrent neural network cell with forward and backward (BPTT) support
  • GRU Cell — gated recurrent unit with reset, update, and new gates
  • RNN Phoneme Classifier — multi-layer RNN for sequence classification
  • Character Predictor — GRU-based character-level prediction with inference utilities
  • CTC Loss — full CTC forward-backward algorithm with posterior probability computation
  • CTC Decoding — greedy search and beam search decoders
  • Neural Network Primitives — Linear layer, Sigmoid, Tanh, Softmax Cross-Entropy loss

Installation

pip install custom-rnn

Quick Start

import numpy as np
from mytorch import RNNCell, GRUCell
from CTC import CTC, CTCLoss, GreedySearchDecoder, BeamSearchDecoder

# Create an RNN cell
rnn = RNNCell(input_size=10, hidden_size=20)
x = np.random.randn(1, 10)
h = np.zeros((1, 20))
h_next = rnn(x, h)

# Create a GRU cell
gru = GRUCell(input_size=10, hidden_size=20)
x = np.random.randn(10)
h = np.zeros(20)
h_next = gru(x, h)

# CTC greedy decoding
symbols = ["a", "b", "c"]
decoder = GreedySearchDecoder(symbols)

# CTC beam search decoding
beam_decoder = BeamSearchDecoder(symbols, beam_width=3)

Requirements

  • Python >= 3.8
  • NumPy

Metadata

Release files for custom-rnn 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for custom-rnn 0.1.0
File
custom_rnn-0.1.0-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details
custom_rnn-0.1.0-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64, Linux glibc 2.5+ x86-64 Details
custom_rnn-0.1.0-cp313-cp313-macosx_11_0_arm64.whl CPython 3.13 CPython 3.13 macOS 11.0+ ARM64 Details
custom_rnn-0.1.0-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details
custom_rnn-0.1.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.5+ x86-64, Linux glibc 2.28+ x86-64 Details
custom_rnn-0.1.0-cp312-cp312-macosx_11_0_arm64.whl CPython 3.12 CPython 3.12 macOS 11.0+ ARM64 Details
custom_rnn-0.1.0-cp311-cp311-win_amd64.whl CPython 3.11 CPython 3.11 Windows x86-64 Details
custom_rnn-0.1.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.5+ x86-64, Linux glibc 2.28+ x86-64 Details
custom_rnn-0.1.0-cp311-cp311-macosx_11_0_arm64.whl CPython 3.11 CPython 3.11 macOS 11.0+ ARM64 Details
custom_rnn-0.1.0-cp310-cp310-win_amd64.whl CPython 3.10 CPython 3.10 Windows x86-64 Details
custom_rnn-0.1.0-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl CPython 3.10 CPython 3.10 Linux glibc 2.5+ x86-64, Linux glibc 2.28+ x86-64 Details
custom_rnn-0.1.0-cp310-cp310-macosx_11_0_arm64.whl CPython 3.10 CPython 3.10 macOS 11.0+ ARM64 Details
custom_rnn-0.1.0-cp39-cp39-win_amd64.whl CPython 3.9 CPython 3.9 Windows x86-64 Details
custom_rnn-0.1.0-cp39-cp39-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl CPython 3.9 CPython 3.9 Linux glibc 2.5+ x86-64, Linux glibc 2.28+ x86-64 Details
custom_rnn-0.1.0-cp39-cp39-macosx_11_0_arm64.whl CPython 3.9 CPython 3.9 macOS 11.0+ ARM64 Details

Total release size: 25.2 MB

Release files / custom_rnn-0.1.0-cp313-cp313-win_amd64.whl

Download URL custom_rnn-0.1.0-cp313-cp313-win_amd64.whl
Size 1.1 MB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
a5b66f310b6249adc276a10abb7c43fc1c25570c47afd9790bb6922da486506c
BLAKE2b-256 checksum
How to use checksums
2bc52b4d01a843edfe8dfb1655c384915bda4e086ac9bba56e8bf6a813fbca88
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl

Download URL custom_rnn-0.1.0-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
Size 2.9 MB
Tags CPython 3.13 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64
SHA-256 checksum
How to use checksums
02b3e4444aa1f54ebc3c1b985c7cd67d16ac809f13f68b162461e25de8b9f028
BLAKE2b-256 checksum
How to use checksums
199692dd01650c09318c5d9f27c81e939157d039abd5a1ebc40fdcca90f976ab
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp313-cp313-macosx_11_0_arm64.whl

Download URL custom_rnn-0.1.0-cp313-cp313-macosx_11_0_arm64.whl
Size 1.1 MB
Tags CPython 3.13 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
26302d8c7ae72d9af35fd9cc5ec4c586e897920e2ea64b6f17d9714e2a99be0c
BLAKE2b-256 checksum
How to use checksums
b0499f02141950520b3806374094cb55e2cf21ce67b65ddda82919ba55783732
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp312-cp312-win_amd64.whl

Download URL custom_rnn-0.1.0-cp312-cp312-win_amd64.whl
Size 1.1 MB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
fa20b60b16d82a298a270b924effaefdea7436457e94db361bd00fcfd511a91a
BLAKE2b-256 checksum
How to use checksums
08561cec75c56203c38e64e87af6d4dcfa7fad00c2f4cc5b6bb67016a15ccc9e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl

Download URL custom_rnn-0.1.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
Size 3.0 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64
SHA-256 checksum
How to use checksums
9d57d6e1d4b9f42f3fc086e0c88b42c9882e60ff11e0b2f035b2a94eca88bb79
BLAKE2b-256 checksum
How to use checksums
054efb992fd6f0ea707978cecccbda65237e5a9fc944d3bc0ef2b75acac05ab8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp312-cp312-macosx_11_0_arm64.whl

Download URL custom_rnn-0.1.0-cp312-cp312-macosx_11_0_arm64.whl
Size 1.1 MB
Tags CPython 3.12 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
46f1606e6ea069f3cf42dec6a090c1630d0d3219da74f31855ed6945b88aacc5
BLAKE2b-256 checksum
How to use checksums
4c21937d827a164cd5fe4388f7d2387876dd0ecbfd2237690951f6b1db700744
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp311-cp311-win_amd64.whl

Download URL custom_rnn-0.1.0-cp311-cp311-win_amd64.whl
Size 1.1 MB
Tags CPython 3.11 Windows x86-64
SHA-256 checksum
How to use checksums
42f7b1b7948eb0dd9509ee8500e6007d8d1edd0a1da20ca03992bd61abcd607e
BLAKE2b-256 checksum
How to use checksums
0874afa272f8a943be20ae677c186d78b859d9b9bacbe71f929ce99d77b6a7b5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl

Download URL custom_rnn-0.1.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
Size 2.9 MB
Tags CPython 3.11 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64
SHA-256 checksum
How to use checksums
9aeb72298485d039021288189d08edb3b2b0d52028252b767568eb285d9dac38
BLAKE2b-256 checksum
How to use checksums
40a004e100e3af28c99ac05c563cd11536fa6cfaaed3fc50091d3f03f0c5c0ff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp311-cp311-macosx_11_0_arm64.whl

Download URL custom_rnn-0.1.0-cp311-cp311-macosx_11_0_arm64.whl
Size 1.1 MB
Tags CPython 3.11 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
c8f8e56a7c93e1d55d51d8c33e0d52b9b5994a62562fa53fd835d36570873e01
BLAKE2b-256 checksum
How to use checksums
c5cca20474e45fb45cbc37f9ebc1160a429165300244db886981934a8528290d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp310-cp310-win_amd64.whl

Download URL custom_rnn-0.1.0-cp310-cp310-win_amd64.whl
Size 1.1 MB
Tags CPython 3.10 Windows x86-64
SHA-256 checksum
How to use checksums
a008a9a3abc4dcfcd723f997e6a77c186dd97e683e978fa2096a077a0579e569
BLAKE2b-256 checksum
How to use checksums
058a234fb16b7ce9e5503e5a87a5b8bfe937513e429befafe291c88e91e0757e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl

Download URL custom_rnn-0.1.0-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
Size 2.7 MB
Tags CPython 3.10 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64
SHA-256 checksum
How to use checksums
890b506b76241e9ad0c3d40fe3fa00d4aec568354e3422d86e08b814411867a3
BLAKE2b-256 checksum
How to use checksums
c10addfeb561a2df7a7b44761117cba955859e5076bcddaf65e27dea35c1c708
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp310-cp310-macosx_11_0_arm64.whl

Download URL custom_rnn-0.1.0-cp310-cp310-macosx_11_0_arm64.whl
Size 1.1 MB
Tags CPython 3.10 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
707865d960be8feca84fbd9c3a81b8c418f3bf10a6e965fcade8350eda471987
BLAKE2b-256 checksum
How to use checksums
ce69ffea0a5b85f9c2d376dd05aaefc5771f518d3e2d4d56be600a81eced1c54
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp39-cp39-win_amd64.whl

Download URL custom_rnn-0.1.0-cp39-cp39-win_amd64.whl
Size 1.1 MB
Tags CPython 3.9 Windows x86-64
SHA-256 checksum
How to use checksums
20f05c57f45c01aa009710f36a13fc33307b126ecceaf66902c88600326176f1
BLAKE2b-256 checksum
How to use checksums
78fd7b79434a468a63d780a0b5fff5044e3ea4013aca97fb27e040bc578ac9fb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp39-cp39-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl

Download URL custom_rnn-0.1.0-cp39-cp39-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl
Size 2.7 MB
Tags CPython 3.9 Linux glibc 2.28+ x86-64 Linux glibc 2.5+ x86-64
SHA-256 checksum
How to use checksums
0ad50646d6a73296cf36cf3e295fbc8a62d1fdf8651ddfcf5c03cc32021aa9ad
BLAKE2b-256 checksum
How to use checksums
6190f40a4ed4469da58bc143f0c4e64b7cb5fa223aea01e209d75c127a121925
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release files / custom_rnn-0.1.0-cp39-cp39-macosx_11_0_arm64.whl

Download URL custom_rnn-0.1.0-cp39-cp39-macosx_11_0_arm64.whl
Size 1.1 MB
Tags CPython 3.9 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
b4f92d38e12d06b92d9935cd4df62749319edfa448989ab600f54a59c94c5352
BLAKE2b-256 checksum
How to use checksums
902f5f7cbd211b3edaf4d595fdf10d26a982ea030fb0a004c5c28017104999b1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 10, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

15 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page