TensorFlowASR

by TensorSpeech

TensorFlow 2 end-to-end ASR — Conformer, ContextNet, DeepSpeech2.

TL;DR

TensorFlow 2 end-to-end ASR — Conformer, ContextNet, DeepSpeech2.

Best for tF2 shops wanting Conformer + Streaming Transducer reference code. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows

What it is

A TF2 implementation of streaming + offline E2E ASR. Apache-2.0.

Best for: TF2 shops wanting Conformer + Streaming Transducer reference code.
Watch out for: Maintenance has slowed; smaller community than PyTorch toolkits.

Install / use

pip install TensorFlowASR

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported10
HIPAA eligibleNo

TensorFlowASR vs Whipscribe

FeatureTensorFlowASRWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages1099
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to TensorFlowASR

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.