Introduction of indicconformer_stt_mr_hybrid_ctc_rnnt_large
Model Details of indicconformer_stt_mr_hybrid_ctc_rnnt_large
IndicConformer
IndicConformer is a Hybrid CTC-RNNT conformer ASR(Automatic Speech Recognition) model.
Language
Marathi
Input
This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
Output
This model provides transcribed speech as a string for a given audio sample.
Model Architecture
This model is a conformer-Large model, consisting of 120M parameters, as the encoder, with a hybrid CTC-RNNT decoder. The model has 17 conformer blocks with
512 as the model dimension.
AI4Bharat NeMo:
To load, train, fine-tune or play with the model you will need to install
AI4Bharat NeMo
. We recommend you install it using the command shown below
model = nemo_asr.models.ASRModel.from_pretrained("ai4bharat/indicconformer_stt_mr_hybrid_rnnt_large")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.freeze() # inference mode
model = model.to(device) # transfer model to device
Get an audio file ready by running the command shown below in your terminal. This will convert the audio to 16000 Hz and monochannel.
indicconformer_stt_mr_hybrid_ctc_rnnt_large huggingface.co is an AI model on huggingface.co that provides indicconformer_stt_mr_hybrid_ctc_rnnt_large's model effect (), which can be used instantly with this ai4bharat indicconformer_stt_mr_hybrid_ctc_rnnt_large model. huggingface.co supports a free trial of the indicconformer_stt_mr_hybrid_ctc_rnnt_large model, and also provides paid use of the indicconformer_stt_mr_hybrid_ctc_rnnt_large. Support call indicconformer_stt_mr_hybrid_ctc_rnnt_large model through api, including Node.js, Python, http.
indicconformer_stt_mr_hybrid_ctc_rnnt_large huggingface.co is an online trial and call api platform, which integrates indicconformer_stt_mr_hybrid_ctc_rnnt_large's modeling effects, including api services, and provides a free online trial of indicconformer_stt_mr_hybrid_ctc_rnnt_large, you can try indicconformer_stt_mr_hybrid_ctc_rnnt_large online for free by clicking the link below.
ai4bharat indicconformer_stt_mr_hybrid_ctc_rnnt_large online free url in huggingface.co:
indicconformer_stt_mr_hybrid_ctc_rnnt_large is an open source model from GitHub that offers a free installation service, and any user can find indicconformer_stt_mr_hybrid_ctc_rnnt_large on GitHub to install. At the same time, huggingface.co provides the effect of indicconformer_stt_mr_hybrid_ctc_rnnt_large install, users can directly use indicconformer_stt_mr_hybrid_ctc_rnnt_large installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
indicconformer_stt_mr_hybrid_ctc_rnnt_large install url in huggingface.co: