diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..a67f417784ac7a31fcc6775ea1b111e2a4708e9d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,90 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tdt_ctc-110m-f16.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-110m-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-110m-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-110m-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-110m-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +realtime_eou_120m-v1-f16.gguf filter=lfs diff=lfs merge=lfs -text +realtime_eou_120m-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +realtime_eou_120m-v1-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +realtime_eou_120m-v1-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +realtime_eou_120m-v1-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text +ctc-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ctc-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v2-f16.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v2-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v2-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v2-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v2-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v3-f16.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v3-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v3-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v3-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-0.6b-v3-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text +ctc-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ctc-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +ctc-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +rnnt-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text +tdt-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tdt-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +tdt_ctc-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text +nemotron-3.5-asr-streaming-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text +nemotron-3.5-asr-streaming-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nemotron-3.5-asr-streaming-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +nemotron-3.5-asr-streaming-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text +nemotron-3.5-asr-streaming-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..254f9352344f28080a925d1857258a605d5f33a3 --- /dev/null +++ b/README.md @@ -0,0 +1,179 @@ +--- +license: cc-by-4.0 +library_name: parakeet.cpp +tags: + - automatic-speech-recognition + - asr + - parakeet + - gguf + - ggml + - cpp-inference + - nemo +pipeline_tag: automatic-speech-recognition +base_model: + - nvidia/parakeet-tdt_ctc-110m + - nvidia/parakeet_realtime_eou_120m-v1 + - nvidia/parakeet-ctc-0.6b + - nvidia/parakeet-rnnt-0.6b + - nvidia/parakeet-tdt-0.6b-v2 + - nvidia/parakeet-tdt-0.6b-v3 + - nvidia/parakeet-ctc-1.1b + - nvidia/parakeet-rnnt-1.1b + - nvidia/parakeet-tdt-1.1b + - nvidia/parakeet-tdt_ctc-1.1b +--- + +# Parakeet GGUF — models for parakeet.cpp + +GGUF-format weights for [parakeet.cpp](https://github.com/mudler/parakeet.cpp), a C++/ggml port of NVIDIA NeMo Parakeet that matches the upstream PyTorch models on CPU. This single repo collects **every supported model × quantization** as a flat set of `.gguf` files — download just the one you need. + +**F16 is the recommended default** — same accuracy as F32, ~1.7× smaller, and typically the fastest on modern CPUs via ggml's F32×F16 matmul fast path. + +## Models + +### tdt_ctc-110m + +Source: [nvidia/parakeet-tdt_ctc-110m](https://huggingface.co/nvidia/parakeet-tdt_ctc-110m) · Hybrid TDT+CTC (FastConformer) · heads: TDT + CTC + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `tdt_ctc-110m-f16.gguf` ← **recommended** | F16 | 267.5 MB | 0.0000 | +| `tdt_ctc-110m-q8_0.gguf` | Q8_0 | 177.8 MB | 0.0000 | +| `tdt_ctc-110m-q6_k.gguf` | Q6_K | 155.9 MB | not measured | +| `tdt_ctc-110m-q5_k.gguf` | Q5_K | 143.3 MB | not measured | +| `tdt_ctc-110m-q4_k.gguf` | Q4_K | 131.4 MB | 0.0000 | + +### realtime_eou_120m-v1 + +Source: [nvidia/parakeet_realtime_eou_120m-v1](https://huggingface.co/nvidia/parakeet_realtime_eou_120m-v1) · Cache-aware streaming RNNT (FastConformer, EOU/EOB) · heads: RNNT (streaming) + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `realtime_eou_120m-v1-f16.gguf` ← **recommended** | F16 | 266.5 MB | not measured | +| `realtime_eou_120m-v1-q8_0.gguf` | Q8_0 | 176.0 MB | not measured | +| `realtime_eou_120m-v1-q6_k.gguf` | Q6_K | 153.9 MB | not measured | +| `realtime_eou_120m-v1-q5_k.gguf` | Q5_K | 141.2 MB | not measured | +| `realtime_eou_120m-v1-q4_k.gguf` | Q4_K | 129.1 MB | not measured | + +### ctc-0.6b + +Source: [nvidia/parakeet-ctc-0.6b](https://huggingface.co/nvidia/parakeet-ctc-0.6b) · CTC (FastConformer) · heads: CTC + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `ctc-0.6b-f16.gguf` ← **recommended** | F16 | 1373.4 MB | 0.0000 | +| `ctc-0.6b-q8_0.gguf` | Q8_0 | 875.4 MB | 0.0000 | +| `ctc-0.6b-q6_k.gguf` | Q6_K | 746.8 MB | not measured | +| `ctc-0.6b-q5_k.gguf` | Q5_K | 676.3 MB | not measured | +| `ctc-0.6b-q4_k.gguf` | Q4_K | 609.9 MB | not measured | + +### rnnt-0.6b + +Source: [nvidia/parakeet-rnnt-0.6b](https://huggingface.co/nvidia/parakeet-rnnt-0.6b) · RNNT transducer (FastConformer) · heads: RNNT + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `rnnt-0.6b-f16.gguf` ← **recommended** | F16 | 1402.8 MB | 0.0000 | +| `rnnt-0.6b-q8_0.gguf` | Q8_0 | 903.9 MB | 0.0000 | +| `rnnt-0.6b-q6_k.gguf` | Q6_K | 776.3 MB | not measured | +| `rnnt-0.6b-q5_k.gguf` | Q5_K | 705.7 MB | not measured | +| `rnnt-0.6b-q4_k.gguf` | Q4_K | 639.2 MB | not measured | + +### tdt-0.6b-v2 + +Source: [nvidia/parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) · TDT transducer (FastConformer) · heads: TDT + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `tdt-0.6b-v2-f16.gguf` ← **recommended** | F16 | 1404.2 MB | 0.0000 | +| `tdt-0.6b-v2-q8_0.gguf` | Q8_0 | 903.8 MB | 0.0000 | +| `tdt-0.6b-v2-q6_k.gguf` | Q6_K | 775.9 MB | not measured | +| `tdt-0.6b-v2-q5_k.gguf` | Q5_K | 705.0 MB | not measured | +| `tdt-0.6b-v2-q4_k.gguf` | Q4_K | 638.4 MB | not measured | + +### tdt-0.6b-v3 + +Source: [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) · TDT transducer (FastConformer) · heads: TDT + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `tdt-0.6b-v3-f16.gguf` ← **recommended** | F16 | 1441.0 MB | 0.0000 | +| `tdt-0.6b-v3-q8_0.gguf` | Q8_0 | 940.7 MB | 0.0000 | +| `tdt-0.6b-v3-q6_k.gguf` | Q6_K | 812.7 MB | not measured | +| `tdt-0.6b-v3-q5_k.gguf` | Q5_K | 741.9 MB | not measured | +| `tdt-0.6b-v3-q4_k.gguf` | Q4_K | 675.2 MB | not measured | + +### ctc-1.1b + +Source: [nvidia/parakeet-ctc-1.1b](https://huggingface.co/nvidia/parakeet-ctc-1.1b) · CTC (FastConformer) · heads: CTC + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `ctc-1.1b-f16.gguf` ← **recommended** | F16 | 2395.8 MB | 0.0000 | +| `ctc-1.1b-q8_0.gguf` | Q8_0 | 1526.3 MB | 0.0000 | +| `ctc-1.1b-q6_k.gguf` | Q6_K | 1301.7 MB | not measured | +| `ctc-1.1b-q5_k.gguf` | Q5_K | 1178.5 MB | not measured | +| `ctc-1.1b-q4_k.gguf` | Q4_K | 1062.6 MB | not measured | + +### rnnt-1.1b + +Source: [nvidia/parakeet-rnnt-1.1b](https://huggingface.co/nvidia/parakeet-rnnt-1.1b) · RNNT transducer (FastConformer) · heads: RNNT + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `rnnt-1.1b-f16.gguf` ← **recommended** | F16 | 2425.2 MB | 0.0000 | +| `rnnt-1.1b-q8_0.gguf` | Q8_0 | 1554.7 MB | 0.0000 | +| `rnnt-1.1b-q6_k.gguf` | Q6_K | 1331.2 MB | not measured | +| `rnnt-1.1b-q5_k.gguf` | Q5_K | 1207.9 MB | not measured | +| `rnnt-1.1b-q4_k.gguf` | Q4_K | 1091.9 MB | not measured | + +### tdt-1.1b + +Source: [nvidia/parakeet-tdt-1.1b](https://huggingface.co/nvidia/parakeet-tdt-1.1b) · TDT transducer (FastConformer) · heads: TDT + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `tdt-1.1b-f16.gguf` ← **recommended** | F16 | 2425.3 MB | 0.0000 | +| `tdt-1.1b-q8_0.gguf` | Q8_0 | 1554.8 MB | 0.0000 | +| `tdt-1.1b-q6_k.gguf` | Q6_K | 1331.2 MB | not measured | +| `tdt-1.1b-q5_k.gguf` | Q5_K | 1207.9 MB | not measured | +| `tdt-1.1b-q4_k.gguf` | Q4_K | 1091.9 MB | not measured | + +### tdt_ctc-1.1b + +Source: [nvidia/parakeet-tdt_ctc-1.1b](https://huggingface.co/nvidia/parakeet-tdt_ctc-1.1b) · Hybrid TDT+CTC (FastConformer) · heads: TDT + CTC + +| File | Variant | Size | WER vs NeMo | +|---|---|---:|---:| +| `tdt_ctc-1.1b-f16.gguf` ← **recommended** | F16 | 2429.5 MB | 0.0000 | +| `tdt_ctc-1.1b-q8_0.gguf` | Q8_0 | 1559.0 MB | 0.0000 | +| `tdt_ctc-1.1b-q6_k.gguf` | Q6_K | 1335.4 MB | not measured | +| `tdt_ctc-1.1b-q5_k.gguf` | Q5_K | 1212.1 MB | not measured | +| `tdt_ctc-1.1b-q4_k.gguf` | Q4_K | 1096.1 MB | not measured | + +> WER (word error rate) is computed against the upstream NeMo reference on `tests/fixtures/speech.wav` (LibriSpeech `2086-149220-0033`, ~7.4 s, English). 0.0 = byte-for-byte identical transcript. See [parity.md](https://github.com/mudler/parakeet.cpp/blob/main/docs/parity.md) and [quantization.md](https://github.com/mudler/parakeet.cpp/blob/main/docs/quantization.md). + +## Quantization notes + +Quantization is applied **only** to the large linear weights fed directly into `ggml_mul_mat` (encoder FFN + attention projections, subsampling output projection, joint enc/pred projections). All other tensors (mel filterbank, LSTM prediction net, conv kernels, batch_norm stats, norms, biases, embeddings) stay F32. + +## Usage + +```bash +# 1. Clone + build parakeet.cpp +git clone https://github.com/mudler/parakeet.cpp +cd parakeet.cpp +cmake -B build -DPARAKEET_BUILD_CLI=ON && cmake --build build -j + +# 2. Download one quant (F16 recommended) +huggingface-cli download mudler/parakeet-cpp-gguf tdt_ctc-110m-f16.gguf --local-dir models/ + +# 3. Transcribe +build/examples/cli/parakeet-cli transcribe \ + --model models/tdt_ctc-110m-f16.gguf \ + --input audio.wav +``` + +## License + +The GGUF weights are derived from the NVIDIA NeMo Parakeet checkpoints, released under the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license. The parakeet.cpp runtime is MIT-licensed. diff --git a/ctc-0.6b-f16.gguf b/ctc-0.6b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..2dccdde7e98d38e7e54a4bf44a745e2254493f14 --- /dev/null +++ b/ctc-0.6b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fcefa21ae78a04d9dedd5d4776535f37e14e252e9c156758a9ace0fd56bafb +size 1373359680 diff --git a/ctc-0.6b-q4_k.gguf b/ctc-0.6b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..d7457a497a600ac625d9d3ffef358b3c6f87d023 --- /dev/null +++ b/ctc-0.6b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439499ecceacae8309f6581f45dc2decb17e3d61e5112de4b4e4fece7483fc0e +size 609898048 diff --git a/ctc-0.6b-q5_k.gguf b/ctc-0.6b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..af31e15ee0c64ed3b32656db2ea5e2c1dd642680 --- /dev/null +++ b/ctc-0.6b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9efeee071776bb1742e15bb79fa613df71cca9c115c89a1c9433fe149082cd +size 676286016 diff --git a/ctc-0.6b-q6_k.gguf b/ctc-0.6b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..7cea404a7758b2c7888966b491444f016f128b49 --- /dev/null +++ b/ctc-0.6b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1183ce28d1013c086063b36b7d8a38f03e19eb7d39ee981e9f5f7e4716df01ab +size 746823232 diff --git a/ctc-0.6b-q8_0.gguf b/ctc-0.6b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..f8a69b7c401f26ab14dc733b36c4057e9e6c7c20 --- /dev/null +++ b/ctc-0.6b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f9815d8f0880b0d87349bc7d277e43d49d61f1941c154d0a40fe38de045cf3 +size 875449920 diff --git a/ctc-1.1b-f16.gguf b/ctc-1.1b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..bd741f8c2cb4163b010f72767b796f06826b8c4a --- /dev/null +++ b/ctc-1.1b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48eac4cf0975f0e31f5a8b857972524e2536363b88ec2bf7147e70bbb006e57b +size 2395800000 diff --git a/ctc-1.1b-q4_k.gguf b/ctc-1.1b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..71e1aa201a2dcd53e65c3b338c03271b093e7ed8 --- /dev/null +++ b/ctc-1.1b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734138ae7262e985bcc9f9d2950542666752606448d83afcb2daa6d946d44640 +size 1062568384 diff --git a/ctc-1.1b-q5_k.gguf b/ctc-1.1b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..d3ec1fb6b1c12f5c42c813f0fdf673ab986e278d --- /dev/null +++ b/ctc-1.1b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116b30d53a6bf5cc470a6c541a43c89a62cef2823ca03127f9efb1054f9c93ee +size 1178501568 diff --git a/ctc-1.1b-q6_k.gguf b/ctc-1.1b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..dd62cb0f4ae673907c12f6f70a4f90beb0f1f744 --- /dev/null +++ b/ctc-1.1b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e7a711383e9a3d279bc083096ca7c38779d20492609d03fa78f3039c93ced2 +size 1301680576 diff --git a/ctc-1.1b-q8_0.gguf b/ctc-1.1b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..e3928ca41de2f59404c4582e3adb9fe5097ea42d --- /dev/null +++ b/ctc-1.1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f9d341173a548af3d5a26aa44aacc34bd2126706f032a25b889f249b51da09 +size 1526301120 diff --git a/nemotron-3.5-asr-streaming-0.6b-f16.gguf b/nemotron-3.5-asr-streaming-0.6b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..1ab78d93fe3c45be0ef91e06cb1030f201d28d5d --- /dev/null +++ b/nemotron-3.5-asr-streaming-0.6b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64413c3886edf2b45eb3e757f911f1bc8020b7cf157622cd0bd0452c6d84aac +size 1484324992 diff --git a/nemotron-3.5-asr-streaming-0.6b-q4_k.gguf b/nemotron-3.5-asr-streaming-0.6b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..798b0291cba4817ececc2590304fc608ef72cfae --- /dev/null +++ b/nemotron-3.5-asr-streaming-0.6b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad85eb3f3014c1a300d67b7ccbd23c38c4c952405cbe33a861e19fb2775e84b +size 718102624 diff --git a/nemotron-3.5-asr-streaming-0.6b-q5_k.gguf b/nemotron-3.5-asr-streaming-0.6b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..62d972528e29e91e3bc9f7e0e2dfbd39cf59e4a9 --- /dev/null +++ b/nemotron-3.5-asr-streaming-0.6b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb14605a707f821560952521034002c91653d676272a80dca0cd2aa886d0ab2 +size 784801888 diff --git a/nemotron-3.5-asr-streaming-0.6b-q6_k.gguf b/nemotron-3.5-asr-streaming-0.6b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..b51aeca3f5b6a7d5f4f4d739379b7c26b4581d28 --- /dev/null +++ b/nemotron-3.5-asr-streaming-0.6b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab1541a9dc7f73cf90f16f0c03c2ae376722a845d41d286be81ccfe17e9d13b +size 855669856 diff --git a/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf b/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..4c3442716c0e9e5265d80292bdc83049a552032f --- /dev/null +++ b/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2f13eccd4a5245be728f77e6149bd6a4fdcdd133ff2e08ac6005bcef7a99f1 +size 983696512 diff --git a/realtime_eou_120m-v1-f16.gguf b/realtime_eou_120m-v1-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..ed79239fc6df540af41ed39308daf5bd8081c927 --- /dev/null +++ b/realtime_eou_120m-v1-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a2b12f12b8a096a57499c9111ed13b442a2b786e17a292c168be45088f0edc +size 266517952 diff --git a/realtime_eou_120m-v1-q4_k.gguf b/realtime_eou_120m-v1-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..6e271606aec7b6f1e4af366d9530e753a7febbe2 --- /dev/null +++ b/realtime_eou_120m-v1-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9109d0e422bd8aafa899c0f58e1938f4a2846838797a29c04f6a8729033c3c +size 129133984 diff --git a/realtime_eou_120m-v1-q5_k.gguf b/realtime_eou_120m-v1-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..e7eb46a33e4534898ccdbacf672965679434fbbb --- /dev/null +++ b/realtime_eou_120m-v1-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e83c13a41751d6130cde836690304cbc143347bdf12577e419018df2235398 +size 141151648 diff --git a/realtime_eou_120m-v1-q6_k.gguf b/realtime_eou_120m-v1-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..e60a28a87b5ee8ca846c641a51724470d8ddb1cd --- /dev/null +++ b/realtime_eou_120m-v1-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4df36abdf2526591236251dcb625a43a8a3d3525bad3791d0a9fa363d5db04 +size 153920416 diff --git a/realtime_eou_120m-v1-q8_0.gguf b/realtime_eou_120m-v1-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..f04807cd01ae3fdc52ff5e9af527ac6ef5937f7a --- /dev/null +++ b/realtime_eou_120m-v1-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62616b914d6f5a683a5dea672df055b57de5c49dddf871b8b44b9c814dc3d896 +size 176001472 diff --git a/rnnt-0.6b-f16.gguf b/rnnt-0.6b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..7a2e71cec62a7609c081362f76a80a142a13c552 --- /dev/null +++ b/rnnt-0.6b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20308eb952a856b217dc52ae89f530fcef09119f4580b0068c1181a70442a8cf +size 1402800800 diff --git a/rnnt-0.6b-q4_k.gguf b/rnnt-0.6b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..722a924ba59673610171e2c0a8b1cb600f9a0314 --- /dev/null +++ b/rnnt-0.6b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e10f0302463cc74262509103275899a0ede3b14f5880162a9b01a72ec74748 +size 639216288 diff --git a/rnnt-0.6b-q5_k.gguf b/rnnt-0.6b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..1278d72ec7a2e3b1b8ef54f1dbc34d65c6c35962 --- /dev/null +++ b/rnnt-0.6b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c132b0131913aa118a7989273d3d34e4309feaac42eff255a988248bad225a +size 705686176 diff --git a/rnnt-0.6b-q6_k.gguf b/rnnt-0.6b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..6f05cb6084038b4c97bf5a3e00f391ded8207ec3 --- /dev/null +++ b/rnnt-0.6b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418dda73f2bafac3ae2207e054f4da50dbf5c4cd7c89a22b702cba12cca40170 +size 776310432 diff --git a/rnnt-0.6b-q8_0.gguf b/rnnt-0.6b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..fc4ce49e4a78c6de68bcbb0ba64792107e16b50c --- /dev/null +++ b/rnnt-0.6b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621326f0dd063f58bee086cb87984e820e4bd9f95f8b1e356b9c552fb5c44843 +size 903892640 diff --git a/rnnt-1.1b-f16.gguf b/rnnt-1.1b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..db1432834f82def0ef3caca5449a39887c14e2ec --- /dev/null +++ b/rnnt-1.1b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981b5941251b5bbbc15bd8672114040ddb697f9b8aae5b15217f445b7cd68e83 +size 2425241120 diff --git a/rnnt-1.1b-q4_k.gguf b/rnnt-1.1b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..a389dd5250cf8002ec544bacfd790a3b23a6eb19 --- /dev/null +++ b/rnnt-1.1b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b19e356f4fd58f18d0832b1c1cf5b6c20818a36a05de07fc0e6e930d813926 +size 1091886624 diff --git a/rnnt-1.1b-q5_k.gguf b/rnnt-1.1b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..005211be7b18753c18f021bd31fbd0e4c17e7edc --- /dev/null +++ b/rnnt-1.1b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74eee48cd26653cb028a76972adafb88498b592312eade592b854f0c5fb58f5 +size 1207901728 diff --git a/rnnt-1.1b-q6_k.gguf b/rnnt-1.1b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..eb6c8c1c559cc034d3da6ca3223bc2cba1dcddb7 --- /dev/null +++ b/rnnt-1.1b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c5b1da998408689aafd0c97aa8aaf093ae96e79b94ba683c9ec9845e7cc82a +size 1331167776 diff --git a/rnnt-1.1b-q8_0.gguf b/rnnt-1.1b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..fbf36cf0eb3746a51d643e520f7c121865715ee9 --- /dev/null +++ b/rnnt-1.1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8423b60c5340d4139bdb4916e091ff8b6433716ceee72c3e885105a306c5cf +size 1554743840 diff --git a/tdt-0.6b-v2-f16.gguf b/tdt-0.6b-v2-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..4ae26064d560ac5702327406596a916a4e96707e --- /dev/null +++ b/tdt-0.6b-v2-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8df7f5dc7b9ceb5cd0637a81194aab5d93022ace555ce81c8969c7a694b8f3d +size 1404218656 diff --git a/tdt-0.6b-v2-q4_k.gguf b/tdt-0.6b-v2-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..abaefa35043a76df26c73f8debe114eab04bebb2 --- /dev/null +++ b/tdt-0.6b-v2-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417e8a8e994ec4bcce7010ab1e205f8b88291a4535ddd3152d24d0e19517bfc8 +size 638373152 diff --git a/tdt-0.6b-v2-q5_k.gguf b/tdt-0.6b-v2-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..b9e08919d688fcc162046702273060e32954c551 --- /dev/null +++ b/tdt-0.6b-v2-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba06d039a2c38d2d1b6b512230ab62ecd04d8bf3be45234dd1ddc507b6393b8 +size 705039648 diff --git a/tdt-0.6b-v2-q6_k.gguf b/tdt-0.6b-v2-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..950f7893cdc91e23bdfc95fa6b6bc1ccafe5d059 --- /dev/null +++ b/tdt-0.6b-v2-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232c382715c568cdb92f51fe8ee18e5f1acb13d8beb4dd6f0250e62da01e99d0 +size 775872800 diff --git a/tdt-0.6b-v2-q8_0.gguf b/tdt-0.6b-v2-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..3b95b8226558bf6c2be82ac53320e3f619a22570 --- /dev/null +++ b/tdt-0.6b-v2-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2027e2e1a4dc60ccdd8558f93b15e7c0db4ef8895b4e82e889f3a6275d8119c6 +size 903835936 diff --git a/tdt-0.6b-v3-f16.gguf b/tdt-0.6b-v3-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..5842e1f1ea0e9370c19860571278c4cb1968ca8c --- /dev/null +++ b/tdt-0.6b-v3-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba47343e1e919895aca90e099150a01ed203ee0942d8ed31e27295efc5abb22 +size 1441046400 diff --git a/tdt-0.6b-v3-q4_k.gguf b/tdt-0.6b-v3-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..dd01c38f64fed5aa26c5f10f031f1553bc89bf1d --- /dev/null +++ b/tdt-0.6b-v3-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993d73feb4206dadda865ab25bd64b50c48dc4d013c3bf6126a721f28b1d5ee8 +size 675200864 diff --git a/tdt-0.6b-v3-q5_k.gguf b/tdt-0.6b-v3-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..817ef1ddf49798e2a22d2ac43deb5be65af63ae9 --- /dev/null +++ b/tdt-0.6b-v3-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ebd1d55609b5ad9dac1c457eeb87a9904f199d6fbbb738453182d010646c2e4 +size 741867360 diff --git a/tdt-0.6b-v3-q6_k.gguf b/tdt-0.6b-v3-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..7b8f743f967bf910f55a78f54949f5d2bb23e7f1 --- /dev/null +++ b/tdt-0.6b-v3-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe7e4631e645463c1f33a597391814bbb9d518b703191e936fb7ccfd2d717aa +size 812700512 diff --git a/tdt-0.6b-v3-q8_0.gguf b/tdt-0.6b-v3-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..b5aaf63253682279578bcc2c33d9c0cd54e8e637 --- /dev/null +++ b/tdt-0.6b-v3-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d69a4a6683f4f2d952bad794c1357ca6eb628027695b4699c5a9ad4cd07d757 +size 940663680 diff --git a/tdt-1.1b-f16.gguf b/tdt-1.1b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..d9a8be6a2e67aa88beb33cc6f4dbee1d962d286f --- /dev/null +++ b/tdt-1.1b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83075a3e00c0fe43248f6b8fac24a29096e4fab28b944dbba7ff380a918b56b5 +size 2425253984 diff --git a/tdt-1.1b-q4_k.gguf b/tdt-1.1b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..96192f9f7fa23df8563ff822aae409ad9407cf2e --- /dev/null +++ b/tdt-1.1b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3dd99c994b9da86f70a1afddf82c5f002c9578b6330855e951c941ebf4dfff +size 1091899488 diff --git a/tdt-1.1b-q5_k.gguf b/tdt-1.1b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..714bfefd7d8ea83c1253a09f31cee242cfb51969 --- /dev/null +++ b/tdt-1.1b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0467c265ce5b630e3905b47038b0ba89811cc1375b0b54eed90144e68da973dc +size 1207914592 diff --git a/tdt-1.1b-q6_k.gguf b/tdt-1.1b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..947c5480da8fdca95d2c88f66e7c029b122e3bb5 --- /dev/null +++ b/tdt-1.1b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8421b395557028ee052ddd0e3b81dbf234e10265e1d9c6b6074131f3f00e14 +size 1331180640 diff --git a/tdt-1.1b-q8_0.gguf b/tdt-1.1b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..401d0fc7fbe7571a12719873aab63fee5a7a60b7 --- /dev/null +++ b/tdt-1.1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0f112a7b30771ff5a01033562118e72f1146f0659fdd5cbba4bd1ac201aade +size 1554756704 diff --git a/tdt_ctc-1.1b-f16.gguf b/tdt_ctc-1.1b-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..2bf80d2fa4ec73e34d975505787b4ec881f5d2d2 --- /dev/null +++ b/tdt_ctc-1.1b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd53f64eefac2623a12f2f118ef50b56622dc3012f42c815c6adf0d08292f387 +size 2429456256 diff --git a/tdt_ctc-1.1b-q4_k.gguf b/tdt_ctc-1.1b-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..c92bc24775968a1712fda9151934cd1c03878c85 --- /dev/null +++ b/tdt_ctc-1.1b-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556016ff60bf585d47fe2c0fa34154c5d543a0170ce41e12daca9620793288fb +size 1096101760 diff --git a/tdt_ctc-1.1b-q5_k.gguf b/tdt_ctc-1.1b-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..0c95bd6b27fa7425a738bb6e43775fe0937ac342 --- /dev/null +++ b/tdt_ctc-1.1b-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534109578c598bef8c5ba0c9f716af388ef5e2b3a960b4eb6cb1230276243df4 +size 1212116864 diff --git a/tdt_ctc-1.1b-q6_k.gguf b/tdt_ctc-1.1b-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..6a34bb691d8fcb64e30661f4f66d1bac3e4eb397 --- /dev/null +++ b/tdt_ctc-1.1b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d032dbbc252c1302ead80e0a1e0f8cbf564072f9a572b7fd63c218e27b34e67e +size 1335382912 diff --git a/tdt_ctc-1.1b-q8_0.gguf b/tdt_ctc-1.1b-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..8ea1df8068365af0098027de86364d5925feffdf --- /dev/null +++ b/tdt_ctc-1.1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1891d7e28d8937ec5b98a27668c637a50f5fd0bdb425076c105f513428b5f7ba +size 1558958976 diff --git a/tdt_ctc-110m-f16.gguf b/tdt_ctc-110m-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..9ec4e2d1933e45fc33a7fb77152aaa5ac17ba43e --- /dev/null +++ b/tdt_ctc-110m-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9a6376edde6a74592ace48b2ebdc27a1ac972d0be9dfcc29e668d99381faf1 +size 267452544 diff --git a/tdt_ctc-110m-q4_k.gguf b/tdt_ctc-110m-q4_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..12a9d665f7a1a4fd200f5e1b0eca8ce76207f3d3 --- /dev/null +++ b/tdt_ctc-110m-q4_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1d90edac07326b20a896440628c50323530cf28c7e7ca99d439bad1dee9abf +size 131387520 diff --git a/tdt_ctc-110m-q5_k.gguf b/tdt_ctc-110m-q5_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..cd09f2684acae76aa2c4d7dac6ddb7267db75e74 --- /dev/null +++ b/tdt_ctc-110m-q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1316a7a708a083179ea133421dc437ceee6719a159489204a1bb6ff559793e5b +size 143290496 diff --git a/tdt_ctc-110m-q6_k.gguf b/tdt_ctc-110m-q6_k.gguf new file mode 100644 index 0000000000000000000000000000000000000000..5ce91efe9b03f7a2fcea31f9be3d1c4c751ac7fa --- /dev/null +++ b/tdt_ctc-110m-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f59dfe19de115845daabfef0a3653c736c8e327719232f638507417e86a3369 +size 155937408 diff --git a/tdt_ctc-110m-q8_0.gguf b/tdt_ctc-110m-q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..82d65c730c472cf9f211c14d2ce4f0481c951387 --- /dev/null +++ b/tdt_ctc-110m-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614feee3a990cf0e672b0314f4da0c80ae8da9094507f5ccb7c42e43b5fc5a12 +size 177796224