Downloads · 30 days
10
12% of all-time downloads
shameez/nemotron-speech-streaming-en-0.6b-onnx-80ms
nemotron-speech-streaming-en-0.6b-onnx-80ms is a automatic speech recognition model from shameez. Use it when you need speech turned into text. The card lists the license as other.
ONNX FP16 export of nvidia/nemotron-speech-streaming-en-0.6b, NVIDIA's 600M-parameter cache-aware streaming ASR model (FastConformer encoder + RNNT decoder), configured for 80ms streaming latency (attcontextsize = [70…
Downloads · 30 days
10
12% of all-time downloads
All-time downloads
85
Public
Repo size
1.3 GB
Likes
0
Public
Click a slice to open those files.
.data1.2 GB · 98%
From the Hugging Face model README
ONNX FP16 export of nvidia/nemotron-speech-streaming-en-0.6b, NVIDIA's 600M-parameter cache-aware streaming ASR model (FastConformer encoder + RNNT decoder), configured for 80ms streaming latency (att_context_size = [70, 0]).
This is a self-export produced directly from NVIDIA's official NeMo checkpoint — not derived from any third-party conversion. The export was made to guarantee clean license provenance and to make the 80ms latency flavor available as a drop-in ONNX model.
License: Governed by the NVIDIA Open Model License Agreement (LICENSE.txt). This is NOT CC-BY-4.0 — a tag that has appeared on some third-party exports of this checkpoint and is incorrect. The source model's correct license is the NVIDIA Open Model License. Provenance: base model revision
7a9b763e6c5fb103da690219c049fac917aa50b1.
pre_encode subsampling front-end is retained in FP32 for converter compatibility; the 24-layer Conformer body runs in FP16.config.json # Machine-readable runtime parameters
shared/
├── filterbank.bin # Mel filterbank weights, shape [1, 128, 257], Slaney norm (131584 bytes)
├── filterbank.meta # "shape=1x128x257"
├── tokens.txt # SentencePiece vocabulary (1024 tokens, "piece id" per line, ids 0–1023)
└── preprocessor.config # Feature extraction parameters (normalize = NA → CMVN OFF)
fp16/
├── encoder_model.onnx # Streaming encoder graph
├── encoder_model.onnx.data # Encoder weights (external data)
├── decoder_model.onnx # RNNT decoder+joint graph
└── decoder_model.onnx.data # Decoder weights (external data)
conversion/
├── export_nemotron.py # NeMo → ONNX export driver
├── convert_fp16.py # FP32 → FP16 conversion
└── dep_baseline_nemo_export_env_macos.txt # Pinned toolkit versions
LICENSE.txt # NVIDIA Open Model License (full text)
NOTICE.txt # Attribution + provenance
All values are in config.json.
| Parameter | Value |
|---|---|
| Sample rate | 16000 Hz |
| Sample format | S16_LE (16-bit signed little-endian) |
| Pre-emphasis | 0.97 |
| FFT size | 512 |
| Hop length | 160 samples (10 ms) |
| Window length | 400 samples (25 ms) |
| Window type | Hann |
| Mel bands | 128 |
| Mel norm | Slaney |
| Mel layout | Band-major [n_mels, n_frames] |
| Normalize (CMVN) | OFF (normalize = NA / null) |
Mel filterbank weights are in shared/filterbank.bin (shape [1, 128, 257]). CMVN is off — the dither value in the config is ignored by the runtime (forced to 0).
| Parameter | Value |
|---|---|
| att_context_size | [70, 0] |
| chunk_mel_frames | 8 |
| pre_encode_cache_frames | 9 |
| total_input_frames | 17 (8 + 9) |
| chunk_audio_samples | 1280 |
| chunk_duration_ms | 80 |
cache_last_channel shape | [1, 24, 70, 1024] (init zeros) |
cache_last_time shape | [1, 24, 1024, 8] (init zeros) |
cache_last_channel_len | [1] int64 (init zero) |
Feed each chunk's cache outputs back as the next chunk's cache inputs.
| Parameter | Value |
|---|---|
| Blank token id | 1024 |
| Vocab size | 1025 (1024 + blank) |
| Max symbols per frame | 10 |
| Prediction layers | 2 (LSTM), hidden 640 |
input_states_1/2 shape | [2, 1, 640] float32 (init zeros) |
# Download
hf download shameez/nemotron-speech-streaming-en-0.6b-onnx-80ms fp16/ shared/ config.json --local-dir ./model
import onnxruntime as ort
encoder = ort.InferenceSession("model/fp16/encoder_model.onnx",
providers=["CPUExecutionProvider"])
decoder = ort.InferenceSession("model/fp16/decoder_model.onnx",
providers=["CPUExecutionProvider"])
# encoder inputs: audio_signal, length, cache_last_channel, cache_last_time, cache_last_channel_len
# decoder inputs: encoder_outputs, targets, target_length, input_states_1, input_states_2
# feed cache outputs back in for streaming
The export + conversion scripts are in conversion/. The exact pinned toolkit versions are in conversion/dep_baseline_nemo_export_env_macos.txt. Export recipe: load the checkpoint with NeMo ASRModel.from_pretrained, set att_context_size=[70, 0], enable cache-aware export (cache_support=True), export to ONNX opset 17, then convert to FP16 with keep_io_types=True (FP32 I/O). See NOTICE.txt for full provenance.
This model is a derivative of nvidia/nemotron-speech-streaming-en-0.6b and is distributed under the NVIDIA Open Model License Agreement (LICENSE.txt). Attribution per Section 3.1 of that license is in NOTICE.txt: "Licensed by NVIDIA Corporation under the NVIDIA Open Model License."