Overview TensorFlowASR implements ASR architectures in TensorFlow 2: Conformer, ContextNet, RNN Transducer and Streaming Conformer (RNNT loss), plus DeepSpeech2 and Jasper (CTC loss). It includes feature extraction, augmentations, greedy and beam search decoders, and training and testing tutorials. Models can be exported to TFLite and run through an ASRInference/ASREngine API, one-shot or streaming.
Who it is for: ML engineers training or deploying custom ASR models in TensorFlow
Strengths Covers Conformer, ContextNet, RNN-T, DeepSpeech2 and Jasper in one codebase TFLite export turns a model into audio-in, text-and-tokens-out Streaming inference; one shared ASREngine decodes many sessions, e.g. one per websocket Installs with uv; extras for CUDA GPU and a script for Cloud TPU Weaknesses TensorFlow-only; no PyTorch or ONNX path mentioned Training needs a git clone to get ctc_decoders and rnnt_loss packages Python 3.12 or 3.13 required, while the badge still says >=3.8 Pretrained model results live in per-example folders, not the main README What it needs GPU optional Docker + Compose Needs TensorFlow, tensorflow-text, uv Models: Conformer, Streaming Conformer, ContextNet, RNN Transducer, DeepSpeech2 What changed From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Voice Rank Project Score 1 voicestudio Desktop app for voice cloning, dubbing, dictation and audiobooks 98 out of 100 score 2 handy Offline push-to-talk dictation app that pastes transcripts into any text field 91 out of 100 score 3 whisper.cpp C/C++ speech-to-text engine running OpenAI Whisper models locally 90 out of 100 score # 4buzz Offline desktop app for transcribing and translating audio with Whisper 84 out of 100 score # 5xiaozhi-esp32 ESP32 firmware for a voice chatbot with MCP device and cloud tool control 83 out of 100 score
How to choose Latency decides usability for voice agents; check the end-to-end numbers the project publishes. Most quality models need a GPU; CPU-only setups are slower and limited to smaller models. Check language coverage and whether models are downloaded at build or at first run. Health
Releases 2 in the last 12 monthsLast one 49 days ago
Top contributor 100% of commits44 of 44 in the last 12 months
Security advisories NoneOn GitHub, in the last 12 months Read from GitHub, deps.dev and OpenSSF on 11 Nov 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check .
License in plain words Apache-2.0 Permissive
Use it at work Yes
Change it and rebrand it Yes
Sell it or host it for others Yes Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.
A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)
Set it up Needs before it works: TensorFlow, tensorflow-text, uv.
Bring in an engineer who knows tensorflowasr . By the hour for upkeep and fixes, or a fixed price for a build. Our own engineering service; it never changes a rank.
Where to run it Referral links: if you sign up through one, we get a commission. They never change a rank.
Ask your AI assistant The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.
Setup for other apps → Claude Code claude mcp add archestack -- npx -y @archestack/mcpCopy
Connector URL https://mcp.archestack.com/mcpCopy
Then ask: Compare tensorflowasr with its top alternatives on Archestack
Share this rank #49 of 88 in Voice on Archestack, as of 12 Nov 2026.
Show it in your README or on your site The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.
Copy for README Copy for your site
Show code README (Markdown)
[](https://archestack.com/best-of-ai/projects/tensorflowasr/)Site or blog (HTML)
<iframe src="https://archestack.com/embed/best-of-ai/tensorflowasr/" title="tensorflowasr on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>How badges work Preview the card
Best of Open-Source AI on GitHub Each review comes from the project's README and facts we check on GitHub. The fix form opens with tensorflowasr filled in.