Model reference · open weights

whisper-tiny.en.tflite

Available as managed deployment Audio nyadla-sys · community Speech→text 1 variants 1k dl/mo

whisper-tiny.en.tflite is an open-weight audio or speech model from nyadla-sys. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bynyadla-sys
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2023-09-03
Popularity1k downloads / month
LicenceOpen weights

About

What whisper-tiny.en.tflite is

Converts OpenAI Whisper speech recognition models to TFLite format for on-device inference (e.g. Android), and generates the mel filter + vocab binary file needed by native C++ runtimes.

Read the full model card

Requirements

  • Python 3.9
  • macOS, Linux, or Google Colab

Dependencies are installed automatically on first run.

Three Generation Modes

The script supports three modes depending on the --language argument:

1. English-only (.en models)

python3.9 whisper_tflite_model_generation_and_test.py --model whisper-tiny.en
  • Output: whisper-tiny.en.tflite
  • Signature: serving_default (transcribe English)
  • forced_decoder_ids: [[2, 50359], [3, 50363]]

2. Single-language (explicit language code)

python3.9 whisper_tflite_model_generation_and_test.py --model whisper-base --language fr
python3.9 whisper_tflite_model_generation_and_test.py --model whisper-base --language de
  • Output: whisper-base.fr.tflite, whisper-base.de.tflite
  • Signature: serving_default (transcribe the specified language)
  • forced_decoder_ids: [[1, ], [2, 50359], [3, 50363]]

3. Transcribe-translate (auto language detection)

python3.9 whisper_tflite_model_generation_and_test.py --model whisper-base --language auto
  • Output: whisper-base-transcribe-translate.tflite
  • Signatures: serving_default (= transcribe), serving_transcribe, serving_translate
  • No language token forced — Whisper auto-detects the spoken language
  • forced_decoder_ids (transcribe): [[2, 50359], [3, 50363]]
  • forced_decoder_ids (translate): [[2, 50358], [3, 50363]]

Usage

# Default: whisper-tiny.en (English-only)
python3.9 whisper_tflite_model_generation_and_test.py

# Single-language French model
python3.9 whisper_tflite_model_generation_and_test.py --model whisper-base --language fr

# Transcribe-translate model (auto-detect language)
python3.9 whisper_tflite_model_generation_and_test.py --model whisper-base --language auto

# Test translate signature specifically
python3.9 whisper_tflite_model_generation_and_test.py --model whisper-small --language auto --task translate

# Show all options
python3.9 whisper_tflite_model_generation_and_test.py --help

Command Line Arguments

ArgumentDefaultDescription
--modelwhisper-tiny.enWhisper model to convert
--languageenLanguage code (en, fr, de, ...) or auto for auto-detection
--tasktranscribetranscribe or translate. Only relevant with --language auto
--multilingual / --no-multilingual--multilingualVocab binary type. Auto-set to --no-multilingual for .en models

Supported Models

ModelTypeParametersRequired VRAMRelative Speed
whisper-tiny.enEnglish-only~39M~1 GB~10x
whisper-tinyMultilingual~39M~1 GB~10x
whisper-base.enEnglish-only~74M~1 GB~7x
whisper-baseMultilingual~74M~1 GB~7x
whisper-small.enEnglish-only~244M~2 GB~4x
whisper-smallMultilingual~244M~2 GB~4x
whisper-medium.enEnglish-only~769M~5 GB~2x
whisper-mediumMultilingual~769M~5 GB~2x
whisper-largeMultilingual~1550M~10 GB1x
whisper-large-v3Multilingual~1550M~10 GB1x
whisper-turboMultilingual~809M~6 GB~8x

Supported Languages

en, fr, hi, ko, de, zh, ja, es, ar, ru, pt, it, nl, sv, pl, da, fi, and many more.

Use auto for language auto-detection. See the full list.

TFLite Serving Signatures

ModeSignaturesDescription
English-only (.en)serving_defaultTranscribe English
Single-languageserving_defaultTranscribe the forced language
Transcribe-translate (auto)serving_default, serving_transcribe, serving_translateAuto-detect language, transcribe or translate to English

Token reference:

  • 50358 = ``
  • 50359 = ``
  • 50363 = ``

What the Script Does

StepDescription
0Install/verify Python dependencies
1Configure model parameters and fetch decoder token mappings
2Load the Whisper model and run a test transcription (English: LibriSpeech, other languages: Google FLEURS)
3Patch TFForceTokensLogitsProcessor to avoid NaN values during TFLite export
4Wrap the model with serving signature(s) and save as TF SavedModel
5Convert the SavedModel to TFLite with dynamic range quantization
6Verify the TFLite model produces correct output via the TFLite Interpreter
7(Optional) Test the TFLite model against .wav audio files
8Generate the mel filters + vocab binary file

Output Files

# English-only
whisper-tiny.en.tflite
filters_vocab_en.bin

# Single-language (e.g. French)
whisper-base.fr.tflite
filters_vocab_multilingual.bin

# Transcribe-translate (auto)
whisper-base-transcribe-translate.tflite
filters_vocab_multilingual.bin

These files are what you need for on-device Whisper inference on Android or other embedded platforms.

Citing

If you are using the Whisper tflite model, please cite:

@misc{nyadla-sys,
  author={Niranjan Yadla},
  title={{Whisper TFLite: OpenAI Whisper Model Port for Edge Devices}},
  year=2022,
  howpublished={GitHub Repository},
  url={https://github.com/nyadla-sys/whisper.tflite},
  url={https://github.com/moonshine-ai/openai-whisper},
  note={Original TFLite implementation of OpenAI Whisper for on-device automatic speech recognition}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys whisper-tiny-en-tflite for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-tiny-en-tflite below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="whisper-tiny-en-tflite" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms