Ir para o conteúdo
ModelListadosExterno
Browse files

Vosk Model Tg

Tajik automatic speech recognition (ASR) model for sherpa-onnx. Architecture is non-streaming Zipformer2.

Fontehuggingface.co/alphacep/vosk-model-tajik/tree/b4900abb39cad697d97d6091a262bbca41fab49c
TipoOtherVersãoRevision b4900abCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
1.002 KB–249 MB
Versão
vRevision b4900ab
Atualizado
31 de out. de 2026
Downloads
0
Fonte
Hugging Face

Descrição da fonte

Vosk Tajik Speech Recognition Model

Tajik automatic speech recognition (ASR) model for sherpa-onnx. Architecture is non-streaming Zipformer2.

Version 0.61

Word Error Rate (WER)

DatasetWER
FLEURS Tajik13.85
Peacockery/tajik-asr-corpus-v3 (test split)28.21

Training Data

This model was trained on Peacockery/tajik-asr-corpus-v3.

Fontes

1 fonte
Hugging FacePrimárioVersão b4900abb39cad697d97d6091a262bbca41fab49c
huggingface.co/alphacep/vosk-model-tajik/tree/b4900abb39cad697d97d6091a262bbca41fab49c

Verificado 31 de out.

Download files

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

3 artefatos

am-onnx/decoder.onnx

onnx · 2,00 MB · SHA-256 8f0165818d79…475f · Hugging Face

Download file

am-onnx/encoder.onnx

onnx · 249 MB · SHA-256 578dbd5fcf69…5be0 · Hugging Face

Download file

am-onnx/joiner.onnx

onnx · 1.002 KB · SHA-256 a1ca9a59dfbe…61a0 · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme15 de ago.huggingface.co/alphacep/vosk-model-tg

--- language: - tg license: apache-2.0 tags: - audio - automatic-speech-recognition - speech - sherpa-onnx - vosk datasets: - Peacockery/tajik-asr-corpus-v3 metrics: - wer pipeline_tag: automatic-speech-recognition model-index: - name: Vosk Tajik Speech Recognition Model results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: FLEURS Tajik type: google/fleurs config: tg_tj split: test metrics: - type: wer value: 13.85 name: Test WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Peacockery/tajik-asr-corpus-v3 type: Peacockery/tajik-asr-corpus-v3 split: test metrics: - type: wer value: 28.21 name: Test WER --- # Vosk Tajik Speech Recognition Model Tajik automatic speech recognition (ASR) model for [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx). Architecture is non-streaming Zipformer2. Version 0.61 ## Word Error Rate (WER) | Dataset | WER | |---------|-----| | [FLEURS Tajik](https://huggingface.co/datasets/google/fleurs) | 13.85 | | [Peacockery/tajik-asr-corpus-v3](https://huggingface.co/datasets/Peacockery/tajik-asr-corpus-v3) (test split) | 28.21 | ## Training Data This model was trained on [Peacockery/tajik-asr-corpus-v3](https://huggingface.co/datasets/Peacockery/tajik-asr-corpus-v3).

Note31 de out.huggingface.co/alphacep/vosk-model-tajik

Source context: 0 downloads · 1 likes · Pipeline automatic-speech-recognition · Repo alphacep/vosk-model-tajik

Note15 de ago.huggingface.co/alphacep/vosk-model-tg

Source context: 0 downloads · 1 likes · Pipeline automatic-speech-recognition · Repo alphacep/vosk-model-tg