Downloads · 30 days
0
valoomba/nemotron-speech-en-0.6b-onnx-1120ms-int4
nemotron-speech-en-0.6b-onnx-1120ms-int4 is a automatic speech recognition model from valoomba. Use it when you need speech turned into text. The card lists the license as other.
A 4-bit (MatMulNBits) quantization of the FP16 1120 ms ONNX export of NVIDIA's nvidia/nemotron-speech-streaming-en-0.6b (English FastConformer encoder + RNN-T transducer, with built-in punctuation & capitalization), f…
Downloads · 30 days
0
Access
Public
Updated Jun 19, 2026
Repo size
469 MB
Likes
0
Public
Click a slice to open those files.
.data468 MB · 100%
From the Hugging Face model README
A 4-bit (MatMulNBits) quantization of the FP16 1120 ms ONNX export of NVIDIA's
nvidia/nemotron-speech-streaming-en-0.6b
(English FastConformer encoder + RNN-T transducer, with built-in punctuation &
capitalization), for running on-device in the browser via onnxruntime-web + WebGPU.
MatMulNBits (217 ops); convs and the small
fused prediction+joint decoder stay higher precision. No ConvInteger, so it loads and runs
on the onnxruntime-web WebGPU execution provider.nvidia/nemotron-speech-streaming-en-0.6b (see LICENSE.txt / NOTICE.txt).shameez/nemotron-speech-streaming-en-0.6b-onnx-1120ms.onnxruntime.quantization.matmul_nbits_quantizer (bits=4, block_size=128) — see quantize.py.| file | precision | notes |
|---|---|---|
encoder_model.onnx (+.data) | int4 | cache-aware streaming FastConformer encoder |
decoder_model.onnx (+.data) | fp16 | fused RNN-T prediction net + joint |
tokens.txt | — | SentencePiece pieces (<piece> <id>), vocab 1024 + blank 1024 |
audio_signal[1,128,121] (112 new + 9 overlap mel frames, log-mel 128/16kHz),
length i64, batch-first caches cache_last_channel[1,24,70,1024] / cache_last_time[1,24,1024,8],
cache_last_channel_len i64 → outputs[1,1024,14] (channel-major) + *_next caches.encoder_outputs[1,1024,1], targets i32, target_length i32,
input_states_1/2[2,1,640] → outputs[…,1025] logits, output_states_1/2. blank id = 1024.