Nalila9633 mudler commited on
Commit
b50b255
·
0 Parent(s):

Duplicate from mudler/parakeet-cpp-gguf

Browse files

Co-authored-by: mudler <mudler@users.noreply.huggingface.co>

This view is limited to 50 files because it contains too many changes.   See raw diff
.gitattributes ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tdt_ctc-110m-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ tdt_ctc-110m-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
+ tdt_ctc-110m-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ tdt_ctc-110m-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
40
+ tdt_ctc-110m-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
41
+ realtime_eou_120m-v1-f16.gguf filter=lfs diff=lfs merge=lfs -text
42
+ realtime_eou_120m-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
43
+ realtime_eou_120m-v1-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
44
+ realtime_eou_120m-v1-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
45
+ realtime_eou_120m-v1-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
46
+ ctc-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
47
+ ctc-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ ctc-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
49
+ ctc-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
50
+ ctc-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
51
+ rnnt-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
52
+ rnnt-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
53
+ rnnt-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
54
+ rnnt-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
55
+ rnnt-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
56
+ tdt-0.6b-v2-f16.gguf filter=lfs diff=lfs merge=lfs -text
57
+ tdt-0.6b-v2-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
58
+ tdt-0.6b-v2-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
59
+ tdt-0.6b-v2-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
60
+ tdt-0.6b-v2-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
61
+ tdt-0.6b-v3-f16.gguf filter=lfs diff=lfs merge=lfs -text
62
+ tdt-0.6b-v3-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
63
+ tdt-0.6b-v3-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
64
+ tdt-0.6b-v3-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
65
+ tdt-0.6b-v3-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
66
+ ctc-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text
67
+ ctc-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
68
+ ctc-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
69
+ ctc-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
70
+ ctc-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
71
+ rnnt-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text
72
+ rnnt-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
73
+ rnnt-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
74
+ rnnt-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
75
+ rnnt-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
76
+ tdt-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text
77
+ tdt-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
78
+ tdt-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
79
+ tdt-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
80
+ tdt-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
81
+ tdt_ctc-1.1b-f16.gguf filter=lfs diff=lfs merge=lfs -text
82
+ tdt_ctc-1.1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
83
+ tdt_ctc-1.1b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
84
+ tdt_ctc-1.1b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
85
+ tdt_ctc-1.1b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
86
+ nemotron-3.5-asr-streaming-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
87
+ nemotron-3.5-asr-streaming-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
88
+ nemotron-3.5-asr-streaming-0.6b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
89
+ nemotron-3.5-asr-streaming-0.6b-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
90
+ nemotron-3.5-asr-streaming-0.6b-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ library_name: parakeet.cpp
4
+ tags:
5
+ - automatic-speech-recognition
6
+ - asr
7
+ - parakeet
8
+ - gguf
9
+ - ggml
10
+ - cpp-inference
11
+ - nemo
12
+ pipeline_tag: automatic-speech-recognition
13
+ base_model:
14
+ - nvidia/parakeet-tdt_ctc-110m
15
+ - nvidia/parakeet_realtime_eou_120m-v1
16
+ - nvidia/parakeet-ctc-0.6b
17
+ - nvidia/parakeet-rnnt-0.6b
18
+ - nvidia/parakeet-tdt-0.6b-v2
19
+ - nvidia/parakeet-tdt-0.6b-v3
20
+ - nvidia/parakeet-ctc-1.1b
21
+ - nvidia/parakeet-rnnt-1.1b
22
+ - nvidia/parakeet-tdt-1.1b
23
+ - nvidia/parakeet-tdt_ctc-1.1b
24
+ ---
25
+
26
+ # Parakeet GGUF — models for parakeet.cpp
27
+
28
+ 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.
29
+
30
+ **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.
31
+
32
+ ## Models
33
+
34
+ ### tdt_ctc-110m
35
+
36
+ Source: [nvidia/parakeet-tdt_ctc-110m](https://huggingface.co/nvidia/parakeet-tdt_ctc-110m) · Hybrid TDT+CTC (FastConformer) · heads: TDT + CTC
37
+
38
+ | File | Variant | Size | WER vs NeMo |
39
+ |---|---|---:|---:|
40
+ | `tdt_ctc-110m-f16.gguf` ← **recommended** | F16 | 267.5 MB | 0.0000 |
41
+ | `tdt_ctc-110m-q8_0.gguf` | Q8_0 | 177.8 MB | 0.0000 |
42
+ | `tdt_ctc-110m-q6_k.gguf` | Q6_K | 155.9 MB | not measured |
43
+ | `tdt_ctc-110m-q5_k.gguf` | Q5_K | 143.3 MB | not measured |
44
+ | `tdt_ctc-110m-q4_k.gguf` | Q4_K | 131.4 MB | 0.0000 |
45
+
46
+ ### realtime_eou_120m-v1
47
+
48
+ 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)
49
+
50
+ | File | Variant | Size | WER vs NeMo |
51
+ |---|---|---:|---:|
52
+ | `realtime_eou_120m-v1-f16.gguf` ← **recommended** | F16 | 266.5 MB | not measured |
53
+ | `realtime_eou_120m-v1-q8_0.gguf` | Q8_0 | 176.0 MB | not measured |
54
+ | `realtime_eou_120m-v1-q6_k.gguf` | Q6_K | 153.9 MB | not measured |
55
+ | `realtime_eou_120m-v1-q5_k.gguf` | Q5_K | 141.2 MB | not measured |
56
+ | `realtime_eou_120m-v1-q4_k.gguf` | Q4_K | 129.1 MB | not measured |
57
+
58
+ ### ctc-0.6b
59
+
60
+ Source: [nvidia/parakeet-ctc-0.6b](https://huggingface.co/nvidia/parakeet-ctc-0.6b) · CTC (FastConformer) · heads: CTC
61
+
62
+ | File | Variant | Size | WER vs NeMo |
63
+ |---|---|---:|---:|
64
+ | `ctc-0.6b-f16.gguf` ← **recommended** | F16 | 1373.4 MB | 0.0000 |
65
+ | `ctc-0.6b-q8_0.gguf` | Q8_0 | 875.4 MB | 0.0000 |
66
+ | `ctc-0.6b-q6_k.gguf` | Q6_K | 746.8 MB | not measured |
67
+ | `ctc-0.6b-q5_k.gguf` | Q5_K | 676.3 MB | not measured |
68
+ | `ctc-0.6b-q4_k.gguf` | Q4_K | 609.9 MB | not measured |
69
+
70
+ ### rnnt-0.6b
71
+
72
+ Source: [nvidia/parakeet-rnnt-0.6b](https://huggingface.co/nvidia/parakeet-rnnt-0.6b) · RNNT transducer (FastConformer) · heads: RNNT
73
+
74
+ | File | Variant | Size | WER vs NeMo |
75
+ |---|---|---:|---:|
76
+ | `rnnt-0.6b-f16.gguf` ← **recommended** | F16 | 1402.8 MB | 0.0000 |
77
+ | `rnnt-0.6b-q8_0.gguf` | Q8_0 | 903.9 MB | 0.0000 |
78
+ | `rnnt-0.6b-q6_k.gguf` | Q6_K | 776.3 MB | not measured |
79
+ | `rnnt-0.6b-q5_k.gguf` | Q5_K | 705.7 MB | not measured |
80
+ | `rnnt-0.6b-q4_k.gguf` | Q4_K | 639.2 MB | not measured |
81
+
82
+ ### tdt-0.6b-v2
83
+
84
+ Source: [nvidia/parakeet-tdt-0.6b-v2](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) · TDT transducer (FastConformer) · heads: TDT
85
+
86
+ | File | Variant | Size | WER vs NeMo |
87
+ |---|---|---:|---:|
88
+ | `tdt-0.6b-v2-f16.gguf` ← **recommended** | F16 | 1404.2 MB | 0.0000 |
89
+ | `tdt-0.6b-v2-q8_0.gguf` | Q8_0 | 903.8 MB | 0.0000 |
90
+ | `tdt-0.6b-v2-q6_k.gguf` | Q6_K | 775.9 MB | not measured |
91
+ | `tdt-0.6b-v2-q5_k.gguf` | Q5_K | 705.0 MB | not measured |
92
+ | `tdt-0.6b-v2-q4_k.gguf` | Q4_K | 638.4 MB | not measured |
93
+
94
+ ### tdt-0.6b-v3
95
+
96
+ Source: [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) · TDT transducer (FastConformer) · heads: TDT
97
+
98
+ | File | Variant | Size | WER vs NeMo |
99
+ |---|---|---:|---:|
100
+ | `tdt-0.6b-v3-f16.gguf` ← **recommended** | F16 | 1441.0 MB | 0.0000 |
101
+ | `tdt-0.6b-v3-q8_0.gguf` | Q8_0 | 940.7 MB | 0.0000 |
102
+ | `tdt-0.6b-v3-q6_k.gguf` | Q6_K | 812.7 MB | not measured |
103
+ | `tdt-0.6b-v3-q5_k.gguf` | Q5_K | 741.9 MB | not measured |
104
+ | `tdt-0.6b-v3-q4_k.gguf` | Q4_K | 675.2 MB | not measured |
105
+
106
+ ### ctc-1.1b
107
+
108
+ Source: [nvidia/parakeet-ctc-1.1b](https://huggingface.co/nvidia/parakeet-ctc-1.1b) · CTC (FastConformer) · heads: CTC
109
+
110
+ | File | Variant | Size | WER vs NeMo |
111
+ |---|---|---:|---:|
112
+ | `ctc-1.1b-f16.gguf` ← **recommended** | F16 | 2395.8 MB | 0.0000 |
113
+ | `ctc-1.1b-q8_0.gguf` | Q8_0 | 1526.3 MB | 0.0000 |
114
+ | `ctc-1.1b-q6_k.gguf` | Q6_K | 1301.7 MB | not measured |
115
+ | `ctc-1.1b-q5_k.gguf` | Q5_K | 1178.5 MB | not measured |
116
+ | `ctc-1.1b-q4_k.gguf` | Q4_K | 1062.6 MB | not measured |
117
+
118
+ ### rnnt-1.1b
119
+
120
+ Source: [nvidia/parakeet-rnnt-1.1b](https://huggingface.co/nvidia/parakeet-rnnt-1.1b) · RNNT transducer (FastConformer) · heads: RNNT
121
+
122
+ | File | Variant | Size | WER vs NeMo |
123
+ |---|---|---:|---:|
124
+ | `rnnt-1.1b-f16.gguf` ← **recommended** | F16 | 2425.2 MB | 0.0000 |
125
+ | `rnnt-1.1b-q8_0.gguf` | Q8_0 | 1554.7 MB | 0.0000 |
126
+ | `rnnt-1.1b-q6_k.gguf` | Q6_K | 1331.2 MB | not measured |
127
+ | `rnnt-1.1b-q5_k.gguf` | Q5_K | 1207.9 MB | not measured |
128
+ | `rnnt-1.1b-q4_k.gguf` | Q4_K | 1091.9 MB | not measured |
129
+
130
+ ### tdt-1.1b
131
+
132
+ Source: [nvidia/parakeet-tdt-1.1b](https://huggingface.co/nvidia/parakeet-tdt-1.1b) · TDT transducer (FastConformer) · heads: TDT
133
+
134
+ | File | Variant | Size | WER vs NeMo |
135
+ |---|---|---:|---:|
136
+ | `tdt-1.1b-f16.gguf` ← **recommended** | F16 | 2425.3 MB | 0.0000 |
137
+ | `tdt-1.1b-q8_0.gguf` | Q8_0 | 1554.8 MB | 0.0000 |
138
+ | `tdt-1.1b-q6_k.gguf` | Q6_K | 1331.2 MB | not measured |
139
+ | `tdt-1.1b-q5_k.gguf` | Q5_K | 1207.9 MB | not measured |
140
+ | `tdt-1.1b-q4_k.gguf` | Q4_K | 1091.9 MB | not measured |
141
+
142
+ ### tdt_ctc-1.1b
143
+
144
+ Source: [nvidia/parakeet-tdt_ctc-1.1b](https://huggingface.co/nvidia/parakeet-tdt_ctc-1.1b) · Hybrid TDT+CTC (FastConformer) · heads: TDT + CTC
145
+
146
+ | File | Variant | Size | WER vs NeMo |
147
+ |---|---|---:|---:|
148
+ | `tdt_ctc-1.1b-f16.gguf` ← **recommended** | F16 | 2429.5 MB | 0.0000 |
149
+ | `tdt_ctc-1.1b-q8_0.gguf` | Q8_0 | 1559.0 MB | 0.0000 |
150
+ | `tdt_ctc-1.1b-q6_k.gguf` | Q6_K | 1335.4 MB | not measured |
151
+ | `tdt_ctc-1.1b-q5_k.gguf` | Q5_K | 1212.1 MB | not measured |
152
+ | `tdt_ctc-1.1b-q4_k.gguf` | Q4_K | 1096.1 MB | not measured |
153
+
154
+ > 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).
155
+
156
+ ## Quantization notes
157
+
158
+ 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.
159
+
160
+ ## Usage
161
+
162
+ ```bash
163
+ # 1. Clone + build parakeet.cpp
164
+ git clone https://github.com/mudler/parakeet.cpp
165
+ cd parakeet.cpp
166
+ cmake -B build -DPARAKEET_BUILD_CLI=ON && cmake --build build -j
167
+
168
+ # 2. Download one quant (F16 recommended)
169
+ huggingface-cli download mudler/parakeet-cpp-gguf tdt_ctc-110m-f16.gguf --local-dir models/
170
+
171
+ # 3. Transcribe
172
+ build/examples/cli/parakeet-cli transcribe \
173
+ --model models/tdt_ctc-110m-f16.gguf \
174
+ --input audio.wav
175
+ ```
176
+
177
+ ## License
178
+
179
+ 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.
ctc-0.6b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fcefa21ae78a04d9dedd5d4776535f37e14e252e9c156758a9ace0fd56bafb
3
+ size 1373359680
ctc-0.6b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439499ecceacae8309f6581f45dc2decb17e3d61e5112de4b4e4fece7483fc0e
3
+ size 609898048
ctc-0.6b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9efeee071776bb1742e15bb79fa613df71cca9c115c89a1c9433fe149082cd
3
+ size 676286016
ctc-0.6b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1183ce28d1013c086063b36b7d8a38f03e19eb7d39ee981e9f5f7e4716df01ab
3
+ size 746823232
ctc-0.6b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f9815d8f0880b0d87349bc7d277e43d49d61f1941c154d0a40fe38de045cf3
3
+ size 875449920
ctc-1.1b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48eac4cf0975f0e31f5a8b857972524e2536363b88ec2bf7147e70bbb006e57b
3
+ size 2395800000
ctc-1.1b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734138ae7262e985bcc9f9d2950542666752606448d83afcb2daa6d946d44640
3
+ size 1062568384
ctc-1.1b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116b30d53a6bf5cc470a6c541a43c89a62cef2823ca03127f9efb1054f9c93ee
3
+ size 1178501568
ctc-1.1b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e7a711383e9a3d279bc083096ca7c38779d20492609d03fa78f3039c93ced2
3
+ size 1301680576
ctc-1.1b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f9d341173a548af3d5a26aa44aacc34bd2126706f032a25b889f249b51da09
3
+ size 1526301120
nemotron-3.5-asr-streaming-0.6b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64413c3886edf2b45eb3e757f911f1bc8020b7cf157622cd0bd0452c6d84aac
3
+ size 1484324992
nemotron-3.5-asr-streaming-0.6b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad85eb3f3014c1a300d67b7ccbd23c38c4c952405cbe33a861e19fb2775e84b
3
+ size 718102624
nemotron-3.5-asr-streaming-0.6b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb14605a707f821560952521034002c91653d676272a80dca0cd2aa886d0ab2
3
+ size 784801888
nemotron-3.5-asr-streaming-0.6b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab1541a9dc7f73cf90f16f0c03c2ae376722a845d41d286be81ccfe17e9d13b
3
+ size 855669856
nemotron-3.5-asr-streaming-0.6b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2f13eccd4a5245be728f77e6149bd6a4fdcdd133ff2e08ac6005bcef7a99f1
3
+ size 983696512
realtime_eou_120m-v1-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a2b12f12b8a096a57499c9111ed13b442a2b786e17a292c168be45088f0edc
3
+ size 266517952
realtime_eou_120m-v1-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9109d0e422bd8aafa899c0f58e1938f4a2846838797a29c04f6a8729033c3c
3
+ size 129133984
realtime_eou_120m-v1-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e83c13a41751d6130cde836690304cbc143347bdf12577e419018df2235398
3
+ size 141151648
realtime_eou_120m-v1-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4df36abdf2526591236251dcb625a43a8a3d3525bad3791d0a9fa363d5db04
3
+ size 153920416
realtime_eou_120m-v1-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62616b914d6f5a683a5dea672df055b57de5c49dddf871b8b44b9c814dc3d896
3
+ size 176001472
rnnt-0.6b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20308eb952a856b217dc52ae89f530fcef09119f4580b0068c1181a70442a8cf
3
+ size 1402800800
rnnt-0.6b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e10f0302463cc74262509103275899a0ede3b14f5880162a9b01a72ec74748
3
+ size 639216288
rnnt-0.6b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c132b0131913aa118a7989273d3d34e4309feaac42eff255a988248bad225a
3
+ size 705686176
rnnt-0.6b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418dda73f2bafac3ae2207e054f4da50dbf5c4cd7c89a22b702cba12cca40170
3
+ size 776310432
rnnt-0.6b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621326f0dd063f58bee086cb87984e820e4bd9f95f8b1e356b9c552fb5c44843
3
+ size 903892640
rnnt-1.1b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981b5941251b5bbbc15bd8672114040ddb697f9b8aae5b15217f445b7cd68e83
3
+ size 2425241120
rnnt-1.1b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b19e356f4fd58f18d0832b1c1cf5b6c20818a36a05de07fc0e6e930d813926
3
+ size 1091886624
rnnt-1.1b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74eee48cd26653cb028a76972adafb88498b592312eade592b854f0c5fb58f5
3
+ size 1207901728
rnnt-1.1b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c5b1da998408689aafd0c97aa8aaf093ae96e79b94ba683c9ec9845e7cc82a
3
+ size 1331167776
rnnt-1.1b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8423b60c5340d4139bdb4916e091ff8b6433716ceee72c3e885105a306c5cf
3
+ size 1554743840
tdt-0.6b-v2-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8df7f5dc7b9ceb5cd0637a81194aab5d93022ace555ce81c8969c7a694b8f3d
3
+ size 1404218656
tdt-0.6b-v2-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417e8a8e994ec4bcce7010ab1e205f8b88291a4535ddd3152d24d0e19517bfc8
3
+ size 638373152
tdt-0.6b-v2-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba06d039a2c38d2d1b6b512230ab62ecd04d8bf3be45234dd1ddc507b6393b8
3
+ size 705039648
tdt-0.6b-v2-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232c382715c568cdb92f51fe8ee18e5f1acb13d8beb4dd6f0250e62da01e99d0
3
+ size 775872800
tdt-0.6b-v2-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2027e2e1a4dc60ccdd8558f93b15e7c0db4ef8895b4e82e889f3a6275d8119c6
3
+ size 903835936
tdt-0.6b-v3-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba47343e1e919895aca90e099150a01ed203ee0942d8ed31e27295efc5abb22
3
+ size 1441046400
tdt-0.6b-v3-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993d73feb4206dadda865ab25bd64b50c48dc4d013c3bf6126a721f28b1d5ee8
3
+ size 675200864
tdt-0.6b-v3-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ebd1d55609b5ad9dac1c457eeb87a9904f199d6fbbb738453182d010646c2e4
3
+ size 741867360
tdt-0.6b-v3-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe7e4631e645463c1f33a597391814bbb9d518b703191e936fb7ccfd2d717aa
3
+ size 812700512
tdt-0.6b-v3-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d69a4a6683f4f2d952bad794c1357ca6eb628027695b4699c5a9ad4cd07d757
3
+ size 940663680
tdt-1.1b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83075a3e00c0fe43248f6b8fac24a29096e4fab28b944dbba7ff380a918b56b5
3
+ size 2425253984
tdt-1.1b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b3dd99c994b9da86f70a1afddf82c5f002c9578b6330855e951c941ebf4dfff
3
+ size 1091899488
tdt-1.1b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0467c265ce5b630e3905b47038b0ba89811cc1375b0b54eed90144e68da973dc
3
+ size 1207914592
tdt-1.1b-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8421b395557028ee052ddd0e3b81dbf234e10265e1d9c6b6074131f3f00e14
3
+ size 1331180640
tdt-1.1b-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0f112a7b30771ff5a01033562118e72f1146f0659fdd5cbba4bd1ac201aade
3
+ size 1554756704
tdt_ctc-1.1b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd53f64eefac2623a12f2f118ef50b56622dc3012f42c815c6adf0d08292f387
3
+ size 2429456256
tdt_ctc-1.1b-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556016ff60bf585d47fe2c0fa34154c5d543a0170ce41e12daca9620793288fb
3
+ size 1096101760
tdt_ctc-1.1b-q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534109578c598bef8c5ba0c9f716af388ef5e2b3a960b4eb6cb1230276243df4
3
+ size 1212116864