ModelAufgelistetExtern

Indic Asr Onnx

INT8-quantized Whisper models in sherpa-onnx format, packaged for on-device speech recognition.

Quellehuggingface.co/ippocode/indic-asr-onnx/tree/1f6243ec6dffc4de2db84fe1446576d1ff52c252

ArtOtherBasismodellkavyamanohar/whisper-small-malayalamVersionRevision 1f6243eCBewertung

Modellquelle

Art: Other
Dateigröße: 12,3–250 MB
Basismodell: kavyamanohar/whisper-small-malayalam
Version: vRevision 1f6243e
Aktualisiert: 27. Sept. 2026
Downloads: 0
Quelle: Hugging Face

Quellenbeschreibung

indic-asr-onnx

INT8-quantized Whisper models in sherpa-onnx format, packaged for on-device speech recognition.

Packs

Each pack contains encoder.int8.onnx, decoder.int8.onnx, and tokens.txt, and is downloaded independently at runtime.

Pack	Languages	Size	Source model
`whisper-tiny`	en, de, fr, es, it, pt, nl, pl (+90 more)	99 MB	openai/whisper-tiny
`whisper-small-ta`	Tamil	358 MB	vasista22/whisper-tamil-small
`whisper-small-hi`	Hindi	358 MB	vasista22/whisper-hindi-small
`whisper-small-ml`	Malayalam	358 MB	kavyamanohar/whisper-small-malayalam
`whisper-tiny-te`	Telugu	99 MB	vasista22/whisper-telugu-tiny
`whisper-tiny-kn`	Kannada	99 MB	vasista22/whisper-kannada-tiny

whisper-tiny is the multilingual base model — it serves all European languages from a single download. The Indic packs are language-specific fine-tunes, which substantially outperform stock Whisper on those languages.

Structure

models/
├── whisper-tiny/
│   ├── encoder.int8.onnx
│   ├── decoder.int8.onnx
│   └── tokens.txt
├── whisper-small-ta/
├── whisper-small-hi/
├── whisper-small-ml/
├── whisper-tiny-te/
└── whisper-tiny-kn/

Usage

Python (sherpa-onnx)

import sherpa_onnx

recognizer = sherpa_onnx.OfflineRecognizer.from_whisper(
    encoder="models/whisper-small-ta/encoder.int8.onnx",
    decoder="models/whisper-small-ta/decoder.int8.onnx",
    tokens="models/whisper-small-ta/tokens.txt",
    language="ta",
    task="transcribe",
    num_threads=2,
)

stream = recognizer.create_stream()
stream.accept_waveform(16000, samples)   # float32 PCM, 16 kHz mono
recognizer.decode_stream(stream)
print(stream.result.text)

Android (Kotlin)

val config = OfflineRecognizerConfig(
    featConfig = FeatureConfig(sampleRate = 16000, featureDim = 80),
    modelConfig = OfflineModelConfig(
        whisper = OfflineWhisperModelConfig(
            encoder = "$packDir/encoder.int8.onnx",
            decoder = "$packDir/decoder.int8.onnx",
            language = "ta",
            task = "transcribe",
        ),
        tokens = "$packDir/tokens.txt",
        numThreads = 2,
    )
)
val recognizer = OfflineRecognizer(config)

Export

Exported with sherpa-onnx's scripts/whisper/export-onnx.py, then dynamically quantized to INT8.

HuggingFace fine-tunes were first converted to OpenAI Whisper checkpoint format ({"dims": ..., "model_state_dict": ...}) so the export script could load them.

Note: on PyTorch ≥ 2.9 the export script requires dynamo=False to be passed to torch.onnx.export — the dynamo-based exporter fails on Whisper's data-dependent positional embedding indexing.

Credits

Fine-tuned Indic models by vasista22 (Speech Lab, IIT Madras — funded by Bhashini, MeitY, Govt. of India) and kavyamanohar
Base models by OpenAI (Whisper)
Export tooling by k2-fsa (sherpa-onnx)

License

Apache 2.0, inherited from the upstream models.

Quellen

1 Quelle

Hugging FacePrimärVersion 1f6243ec6dffc4de2db84fe1446576d1ff52c252

huggingface.co/ippocode/indic-asr-onnx/tree/1f6243ec6dffc4de2db84fe1446576d1ff52c252

Verifiziert 30. Aug.

Modellartefakte

12 Artefakte

models/whisper-small-hi/decoder.int8.onnx

onnx · 250 MB · SHA-256 9f2ab915e2b4…d99a · Hugging Face

Herunterladen

models/whisper-small-hi/encoder.int8.onnx

onnx · 107 MB · SHA-256 37a8f9a573a3…ea7b · Hugging Face

Herunterladen

models/whisper-small-ml/decoder.int8.onnx

onnx · 250 MB · SHA-256 e96e9bbdd74a…2454 · Hugging Face

Herunterladen

models/whisper-small-ml/encoder.int8.onnx

onnx · 107 MB · SHA-256 4af8b7165d3f…a71b · Hugging Face

Herunterladen

models/whisper-small-ta/decoder.int8.onnx

onnx · 250 MB · SHA-256 672e9a3e19b1…f5e3 · Hugging Face

Herunterladen

models/whisper-small-ta/encoder.int8.onnx

onnx · 107 MB · SHA-256 c5564b49e9c8…0b05 · Hugging Face

Herunterladen

models/whisper-tiny-kn/decoder.int8.onnx

onnx · 85,7 MB · SHA-256 5c4990b7ff18…cbb7 · Hugging Face

Herunterladen

models/whisper-tiny-kn/encoder.int8.onnx

onnx · 12,3 MB · SHA-256 6bf330b8f761…51ce · Hugging Face

Herunterladen

models/whisper-tiny-te/decoder.int8.onnx

onnx · 85,7 MB · SHA-256 b8826b9c860a…59f3 · Hugging Face

Herunterladen

models/whisper-tiny-te/encoder.int8.onnx

onnx · 12,3 MB · SHA-256 c429168b353c…e431 · Hugging Face

Herunterladen

models/whisper-tiny/decoder.int8.onnx

onnx · 85,7 MB · SHA-256 4f35a102081f…701a · Hugging Face

Herunterladen

models/whisper-tiny/encoder.int8.onnx

onnx · 12,3 MB · SHA-256 d71c2315088f…7605 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme30. Aug.huggingface.co/ippocode/indic-asr-onnx

--- license: apache-2.0 language: - en - de - fr - es - it - pt - nl - pl - ta - hi - te - kn - ml tags: - automatic-speech-recognition - whisper - sherpa-onnx - onnx - on-device - quantized library_name: sherpa-onnx pipeline_tag: automatic-speech-recognition base_model: - openai/whisper-tiny - vasista22/whisper-tamil-small - vasista22/whisper-hindi-small - vasista22/whisper-telugu-tiny - vasista22/whisper-kannada-tiny - kavyamanohar/whisper-small-malayalam --- # indic-asr-onnx INT8-quantized Whisper models in [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) format, packaged for on-device speech recognition. ## Packs Each pack contains `encoder.int8.onnx`, `decoder.int8.onnx`, and `tokens.txt`, and is downloaded independently at runtime. | Pack | Languages | Size | Source model | |---|---|---|---| | `whisper-tiny` | en, de, fr, es, it, pt, nl, pl (+90 more) | 99 MB | [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | | `whisper-small-ta` | Tamil | 358 MB | [vasista22/whisper-tamil-small](https://huggingface.co/vasista22/whisper-tamil-small) | | `whisper-small-hi` | Hindi | 358 MB | [vasista22/whisper-hindi-small](https://huggingface.co/vasista22/whisper-hindi-small) | | `whisper-small-ml` | Malayalam | 358 MB | [kavyamanohar/whisper-small-malayalam](https://huggingface.co/kavyamanohar/whisper-small-malayalam) | | `whisper-tiny-te` | Telugu | 99 MB | [vasista22/whisper-telugu-tiny](https://huggingface.co/vasista22/whisper-telugu-tiny) | | `whisper-tiny-kn` | Kannada | 99 MB | [vasista22/whisper-kannada-tiny](https://huggingface.co/vasista22/whisper-kannada-tiny) | `whisper-tiny` is the multilingual base model — it serves all European languages from a single download. The Indic packs are language-specific fine-tunes, which substantially outperform stock Whisper on those languages. ## Structure ``` models/ ├── whisper-tiny/ │ ├── encoder.int8.onnx │ ├── decoder.int8.onnx │ └── tokens.txt ├── whisper-small-ta/ ├── whisper-small-hi/ ├── whisper-small-ml/ ├── whisper-tiny-te/ └── whisper-tiny-kn/ ``` ## Usage ### Python (sherpa-onnx) ```python import sherpa_onnx recognizer = sherpa_onnx.OfflineRecognizer.from_whisper( encoder="models/whisper-small-ta/encoder.int8.onnx", decoder="models/whisper-small-ta/decoder.int8.onnx", tokens="models/whisper-small-ta/tokens.txt", language="ta", task="transcribe",...

Note30. Aug.huggingface.co/ippocode/indic-asr-onnx

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Library sherpa-onnx · Repo ippocode/indic-asr-onnx