Compare model versions
Earlier snapshot
Snapshot #243
Repository revision
07cee06 (opens in a new tab)
Recorded at 04 Sep 2026, 13:42 UTC
Unchanged through 11 Sep 2026, 06:14 UTC
Later snapshot
Snapshot #314
Repository revision
e9a6601 (opens in a new tab)
Recorded at 14 Sep 2026, 05:31 UTC
Summary
Licence
UnchangedNo change
CC-BY-4.0
CC-BY-4.0
PinDiff reports the declared licence and licence files. It does not interpret licence terms.
Weights
UnchangedNo change
Remote code / configuration
UnchangedNo change
Remote code
No
No
Access / gating
UnchangedNo change
Public
Public
Model card
ChangedModel card modified (2 sections)
Metadata (front matter) Changed Material section +8 −5
Diff
⋯ 14 unchanged lines
- rnnt
- tdt
transcribe_cpp:
Added: + schema_version: 2
Added: + wer_fleurs_en:
Added: + q8_0: 4.11
wer_librispeech_test_clean:
f32: 1.68
f16: 1.68
⋯ 1 unchanged line
q6_k: 1.7
q5_k_m: 1.7
q4_k_m: 1.72
Removed: - rtf_ryzen_4750u:
Removed: - cpu: 8
Removed: - vulkan: 15
rtf_m4_max:
Removed: - cpu: 29
Removed: - metal: 175
Added: + cpu: 29.0
Added: + metal: 175.0
Added: + rtf_ryzen_4750u:
Added: + cpu: 7.99
Added: + vulkan: 15.43
streaming: false
translate: false
lang_detect: false
Before
license: cc-by-4.0
base_model: nvidia/parakeet-tdt-0.6b-v2
base_model_relation: quantized
library_name: transcribe.cpp
pipeline_tag: automatic-speech-recognition
language:
- en
tags:
- gguf
- transcribe.cpp
- asr
- speech-to-text
- parakeet
- conformer
- rnnt
- tdt
transcribe_cpp:
wer_librispeech_test_clean:
f32: 1.68
f16: 1.68
q8_0: 1.69
q6_k: 1.7
q5_k_m: 1.7
q4_k_m: 1.72
rtf_ryzen_4750u:
cpu: 8
vulkan: 15
rtf_m4_max:
cpu: 29
metal: 175
streaming: false
translate: false
lang_detect: false
timestamps: token
After
license: cc-by-4.0
base_model: nvidia/parakeet-tdt-0.6b-v2
base_model_relation: quantized
library_name: transcribe.cpp
pipeline_tag: automatic-speech-recognition
language:
- en
tags:
- gguf
- transcribe.cpp
- asr
- speech-to-text
- parakeet
- conformer
- rnnt
- tdt
transcribe_cpp:
schema_version: 2
wer_fleurs_en:
q8_0: 4.11
wer_librispeech_test_clean:
f32: 1.68
f16: 1.68
q8_0: 1.69
q6_k: 1.7
q5_k_m: 1.7
q4_k_m: 1.72
rtf_m4_max:
cpu: 29.0
metal: 175.0
rtf_ryzen_4750u:
cpu: 7.99
vulkan: 15.43
streaming: false
translate: false
lang_detect: false
timestamps: token
Downloads Changed +8 −7
Diff
⋯ 2 unchanged lines
| F32 | [parakeet-tdt-0.6b-v2-F32.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F32.gguf) | 2.47 GB | 1.68% |
| F16 | [parakeet-tdt-0.6b-v2-F16.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F16.gguf) | 1.24 GB | 1.68% |
| Q8_0 | [parakeet-tdt-0.6b-v2-Q8_0.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q8_0.gguf) | 730 MB | 1.69% |
Removed: - | Q6_K | [parakeet-tdt-0.6b-v2-Q6_K.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q6_K.gguf) | 608 MB | 1.70% |
Removed: - | Q5_K_M | [parakeet-tdt-0.6b-v2-Q5_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q5_K_M.gguf) | 547 MB | 1.70% |
Removed: - | Q4_K_M | [parakeet-tdt-0.6b-v2-Q4_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q4_K_M.gguf) | 483 MB | 1.72% |
Added: + | Q6_K | [parakeet-tdt-0.6b-v2-Q6_K.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q6_K.gguf) | 600 MB | 1.70% |
Added: + | Q5_K_M | [parakeet-tdt-0.6b-v2-Q5_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q5_K_M.gguf) | 539 MB | 1.70% |
Added: + | Q4_K_M | [parakeet-tdt-0.6b-v2-Q4_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q4_K_M.gguf) | 475 MB | 1.72% |
Removed: - WER measured on the full LibriSpeech test-clean split (2620 utterances) with
Removed: - greedy transducer decoding and no external LM. F32 reference baseline: 1.68%.
Removed: - NVIDIA's self-reported number on the same split is 1.69%, so the F32 and Q8_0
Removed: - ports match the upstream reference within rounding.
Added: + WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
Added: +
Added: + Greedy transducer decoding, no external LM. F32 reference baseline: 1.68%. NVIDIA's
Added: + self-reported number on the same split is 1.69%, so the F32 and Q8_0 ports match the
Added: + upstream reference within rounding.
Before
| Quantization | Download | Size | WER (LibriSpeech test-clean) | | --- | --- | ---: | ---: | | F32 | [parakeet-tdt-0.6b-v2-F32.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F32.gguf) | 2.47 GB | 1.68% | | F16 | [parakeet-tdt-0.6b-v2-F16.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F16.gguf) | 1.24 GB | 1.68% | | Q8_0 | [parakeet-tdt-0.6b-v2-Q8_0.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q8_0.gguf) | 730 MB | 1.69% | | Q6_K | [parakeet-tdt-0.6b-v2-Q6_K.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q6_K.gguf) | 608 MB | 1.70% | | Q5_K_M | [parakeet-tdt-0.6b-v2-Q5_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q5_K_M.gguf) | 547 MB | 1.70% | | Q4_K_M | [parakeet-tdt-0.6b-v2-Q4_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q4_K_M.gguf) | 483 MB | 1.72% | WER measured on the full LibriSpeech test-clean split (2620 utterances) with greedy transducer decoding and no external LM. F32 reference baseline: 1.68%. NVIDIA's self-reported number on the same split is 1.69%, so the F32 and Q8_0 ports match the upstream reference within rounding.
After
| Quantization | Download | Size | WER (LibriSpeech test-clean) | | --- | --- | ---: | ---: | | F32 | [parakeet-tdt-0.6b-v2-F32.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F32.gguf) | 2.47 GB | 1.68% | | F16 | [parakeet-tdt-0.6b-v2-F16.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-F16.gguf) | 1.24 GB | 1.68% | | Q8_0 | [parakeet-tdt-0.6b-v2-Q8_0.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q8_0.gguf) | 730 MB | 1.69% | | Q6_K | [parakeet-tdt-0.6b-v2-Q6_K.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q6_K.gguf) | 600 MB | 1.70% | | Q5_K_M | [parakeet-tdt-0.6b-v2-Q5_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q5_K_M.gguf) | 539 MB | 1.70% | | Q4_K_M | [parakeet-tdt-0.6b-v2-Q4_K_M.gguf](https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf/resolve/main/parakeet-tdt-0.6b-v2-Q4_K_M.gguf) | 475 MB | 1.72% | WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded. Greedy transducer decoding, no external LM. F32 reference baseline: 1.68%. NVIDIA's self-reported number on the same split is 1.69%, so the F32 and Q8_0 ports match the upstream reference within rounding.
38 other sections unchanged.
Repository status
ChangedRepository revision moved
- Earlier
-
Revision
07cee06(opens in a new tab) · 8 files · 6.05 GB - Later
-
Revision
e9a6601(opens in a new tab) · 8 files · 6.05 GB
A new revision does not by itself mean files changed; the categories above show what differs.
Files
UnchangedNo change
Evidence observed by PinDiff from the Hugging Face API and stored when recorded. PinDiff compares stored metadata, hashes and text files; it does not download weight files. Change events recorded between these snapshots