Commit History
-
docs: link tested any-to-any pipeline and state ASR task boundary
LauraGPTUnverified signatureSigned-off-by: LauraGPT <18321252+LauraGPT@users.noreply.github.com>7ef6caf -
docs: link tested native CUDA transcription recipe
LauraGPTUnverified signatureSigned-off-by: LauraGPT <18321252+LauraGPT@users.noreply.github.com>e8260dc
-
docs: lead with released native Transformers examples
zhifu gaoUnverified signatureSigned-off-by: zhifu gao <zhifu.gzf@alibaba-inc.com>a849aa4 -
docs: align native quickstart with merged Transformers support
zhifu gaoUnverified signatureSigned-off-by: zhifu gao <zhifu.gzf@alibaba-inc.com>b4d4bb9
-
Reconvert Fun-ASR-Nano for reviewed Transformers architecture
Verified signatureConverted with Transformers 53813aeb137e1bdc343bb62b60306ee346c2040b from original checkpoint 272c57b82523ada6fd87095e955f8e29100979ab. Chinese, English and mixed-batch generation validated locally on H100; no missing, unexpected or mismatched keys. Preserves model-card content with matching install/doc commit links.d93b302
-
Update checkpoint for canonical audio configuration
Verified signature1fd03aa -
docs: clarify Transformers checkpoint CTC capability boundary
Verified signaturef1ff8a9 -
Fix Fun-ASR-Nano processor LFR config field names for Transformers #46180
Verified signaturee45779d
-
Reconvert checkpoint for transformers PR #46180
Verified signatureReconverted from FunAudioLLM/Fun-ASR-Nano-2512 with transformers PR #46180 exact head 54c3e74569bbee61a15c2e62d29ae2b1dcaf9702. Local verification loaded 1,540 tensors with zero missing, unexpected, mismatched, or error keys and passed Chinese, English, and mixed-batch H100 transcription checks.67628a9
-
docs: use canonical FunASR ecosystem links
Verified signaturePoint Fun-ASR and SenseVoice links at their canonical QwenAudio repositories. Keep deployment links current; the Transformers card also pins the verified PR head.972ee60
-
Update Transformers quickstart for PR 46180
Verified signaturePin the verified rebased PR head, document structured language/context/hotword inputs, and remove the obsolete serialized default prompt field.e296c62 -
Preserve all transcription context and keywords
Verified signaturec9a572e -
Update structured transcription chat template
Verified signaturef7a3431
-
Link model card to FunAudioLLM paper (#3)
- Link model card to FunAudioLLM paper (f0b6d44d388b0b643d71ceee3e1df332b0ff48a5)854d88f
-
Refresh checkpoint for shared Whisper component layout (#2)
- Refresh checkpoint for shared Whisper component layout (6367f428c1f41cef6782b1ec6afe9bd50940ef90) - Regenerate checkpoint for current Transformers layout (c49669b7536c4c13ca86b9abdfcef18b8a5e5737)c0248cc
-
docs: add tested Transformers PR install command
zhifu gaob8b7ac6
-
docs: clarify Nano language coverage (#1)
- docs: clarify Nano language coverage (6715224cf0a749bc092b2dec9d76057537e3f630)e711f3d
-
Update split-layout Transformers checkpoint
Verified signaturePublish the checkpoint and processor artifacts validated for huggingface/transformers#46180. The model loads with zero missing, unexpected, or mismatched keys and passes the H100 English transcription quickstart. Also replace the stale preprocessor config and add model-card usage instructions.4d5668e
-
Re-convert Fun-ASR-Nano to dtype-consistent bf16 (modular split layout); shrink 2.75GB->1.97GB
Verified signature35bf550 -
Re-convert Fun-ASR-Nano to dtype-consistent bf16 (modular split layout); shrink 2.75GB->1.97GB
Verified signature2aa316d
-
Add chat_template.jinja for transformers apply_chat_template
Verified signaturef2ba1bd -
docs: add FunASR ecosystem GitHub Star links
3ecd9e9
-
Add README with pipeline_tag: automatic-speech-recognition
Zhifu Gao9436970
-
Add Fun-ASR-Nano in HuggingFace Transformers format (safetensors)
Verified signature1b829ba -
initial commit
Verified signatureb405a1c