ai4bharat / indicconformer_stt_ta_hybrid_ctc_rnnt_large

huggingface.co
Total runs: 107
24-hour runs: -13
7-day runs: 54
30-day runs: 413
Model's Last Updated: Novembre 04 2024
automatic-speech-recognition

Introduction of indicconformer_stt_ta_hybrid_ctc_rnnt_large

Model Details of indicconformer_stt_ta_hybrid_ctc_rnnt_large

IndicConformer

IndicConformer is a Hybrid CTC-RNNT conformer ASR(Automatic Speech Recognition) model.

Language

Tamil

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

git clone https://github.com/AI4Bharat/NeMo.git && cd NeMo && git checkout nemo-v2 && bash reinstall.sh
Usage

Download and load the model from Huggingface.

model = nemo_asr.models.ASRModel.from_pretrained("ai4bharat/indicconformer_stt_ta_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.

ffmpeg -i sample_audio.wav -ac 1 -ar 16000 sample_audio_infer_ready.wav
Inference using CTC decoder
model.cur_decoder = "ctc"
ctc_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1,logprobs=False, language_id='ta')[0]
print(ctc_text)
Inference using RNNT decoder
model.cur_decoder = "rnnt"
rnnt_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1, language_id='ta')[0]
print(rnnt_text)

Runs of ai4bharat indicconformer_stt_ta_hybrid_ctc_rnnt_large on huggingface.co

107
Total runs
-13
24-hour runs
2
3-day runs
54
7-day runs
413
30-day runs

More Information About indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co Model

More indicconformer_stt_ta_hybrid_ctc_rnnt_large license Visit here:

https://choosealicense.com/licenses/mit

indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co

indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co is an AI model on huggingface.co that provides indicconformer_stt_ta_hybrid_ctc_rnnt_large's model effect (), which can be used instantly with this ai4bharat indicconformer_stt_ta_hybrid_ctc_rnnt_large model. huggingface.co supports a free trial of the indicconformer_stt_ta_hybrid_ctc_rnnt_large model, and also provides paid use of the indicconformer_stt_ta_hybrid_ctc_rnnt_large. Support call indicconformer_stt_ta_hybrid_ctc_rnnt_large model through api, including Node.js, Python, http.

indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co Url

https://huggingface.co/ai4bharat/indicconformer_stt_ta_hybrid_ctc_rnnt_large

ai4bharat indicconformer_stt_ta_hybrid_ctc_rnnt_large online free

indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co is an online trial and call api platform, which integrates indicconformer_stt_ta_hybrid_ctc_rnnt_large's modeling effects, including api services, and provides a free online trial of indicconformer_stt_ta_hybrid_ctc_rnnt_large, you can try indicconformer_stt_ta_hybrid_ctc_rnnt_large online for free by clicking the link below.

ai4bharat indicconformer_stt_ta_hybrid_ctc_rnnt_large online free url in huggingface.co:

https://huggingface.co/ai4bharat/indicconformer_stt_ta_hybrid_ctc_rnnt_large

indicconformer_stt_ta_hybrid_ctc_rnnt_large install

indicconformer_stt_ta_hybrid_ctc_rnnt_large is an open source model from GitHub that offers a free installation service, and any user can find indicconformer_stt_ta_hybrid_ctc_rnnt_large on GitHub to install. At the same time, huggingface.co provides the effect of indicconformer_stt_ta_hybrid_ctc_rnnt_large install, users can directly use indicconformer_stt_ta_hybrid_ctc_rnnt_large installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

indicconformer_stt_ta_hybrid_ctc_rnnt_large install url in huggingface.co:

https://huggingface.co/ai4bharat/indicconformer_stt_ta_hybrid_ctc_rnnt_large

Url of indicconformer_stt_ta_hybrid_ctc_rnnt_large

indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co Url

Provider of indicconformer_stt_ta_hybrid_ctc_rnnt_large huggingface.co

ai4bharat
ORGANIZATIONS

Other API from ai4bharat

huggingface.co

Total runs: 1.2M
Run Growth: 781.7K
Growth Rate: 67.75%
Updated: Août 07 2022
huggingface.co

Total runs: 46.8K
Run Growth: 1.5K
Growth Rate: 3.13%
Updated: Décembre 21 2022
huggingface.co

Total runs: 1.7K
Run Growth: 311
Growth Rate: 18.14%
Updated: Août 07 2022
huggingface.co

Total runs: 1.1K
Run Growth: -3.1K
Growth Rate: -277.26%
Updated: Mars 11 2024
huggingface.co

Total runs: 223
Run Growth: -81
Growth Rate: -23.62%
Updated: Octobre 18 2024
huggingface.co

Total runs: 24
Run Growth: 9
Growth Rate: 42.86%
Updated: Octobre 18 2024
huggingface.co

Total runs: 18
Run Growth: 7
Growth Rate: 30.43%
Updated: Octobre 18 2024
huggingface.co

Total runs: 12
Run Growth: -3
Growth Rate: -11.54%
Updated: Octobre 18 2024
huggingface.co

Total runs: 3
Run Growth: 17
Growth Rate: 56.67%
Updated: Octobre 18 2024
huggingface.co

Total runs: 3
Run Growth: 10
Growth Rate: 40.00%
Updated: Octobre 18 2024