summaryrefslogtreecommitdiff
path: root/candle-examples/examples/whisper
Commit message (Expand)AuthorAgeFilesLines
* Add required feature for whisper example in Readme (#2539)dengelt2024-10-041-1/+1
* Add whisper large-v3 turbo to the example. (#2531)Laurent Mazare2024-10-021-0/+3
* whisper readme (#1899)Sanchit Gandhi2024-03-211-3/+4
* support distil-large-v3 (#1898)Sanchit Gandhi2024-03-211-1/+5
* Supports more audio formats (#1628)Hubert Shelley2024-02-032-10/+79
* Quantized GGUF style (#1523)Nicolas Patry2024-01-171-2/+4
* Use the whisper-v3 tokenizer now that it has been added. (#1337)Laurent Mazare2023-11-161-6/+8
* Add the mel filters for 128 bins. (#1295)Laurent Mazare2023-11-082-1/+5
* Preliminary support for whisper v3. (#1294)Laurent Mazare2023-11-081-9/+19
* Add support for distil whisper (#1245)Laurent Mazare2023-11-021-3/+15
* Simd128 optimized q8k vecdot. (#1026)Laurent Mazare2023-10-031-1/+1
* Improve the quantized whisper setup. (#1018)Laurent Mazare2023-10-021-9/+17
* Add a quantized variant of whisper (#1017)Laurent Mazare2023-10-022-44/+95
* Adapt more examples to the updated safetensor api. (#947)Laurent Mazare2023-09-231-3/+2
* Add more example readmes. (#828)Laurent Mazare2023-09-121-0/+39
* Move some models to candle-transformers so that it's easier to re-use. (#794)Laurent Mazare2023-09-104-679/+24
* Add tracing to segment-anything (#777)Laurent Mazare2023-09-081-1/+0
* Whisper fix (#711)Laurent Mazare2023-09-012-9/+3
* Fix the accelerate build (#678)Laurent Mazare2023-08-301-4/+3
* Dilated convolutions (#657)Laurent Mazare2023-08-291-0/+2
* Remove some dead-code annotations. (#629)Laurent Mazare2023-08-271-28/+0
* Add some group parameter to convolutions. (#566)Laurent Mazare2023-08-231-0/+2
* Put the transcribe token before the language one. (#553)Laurent Mazare2023-08-221-3/+3
* Improve the timestamps support in whisper (#539)Laurent Mazare2023-08-211-4/+74
* Add a simple Module trait and implement it for the various nn layers (#500)Laurent Mazare2023-08-181-1/+1
* Use the main branch of the HF repo where possible. (#498)Laurent Mazare2023-08-181-3/+7
* Add medium model (#497)Franco Lucchini2023-08-181-1/+3
* Replicate the sot-token logic from the Python implementation more acc… (#491)Laurent Mazare2023-08-171-3/+49
* Add the whisper small model. (#490)Laurent Mazare2023-08-171-2/+8
* Add a cuda kernel for upsampling. (#441)Laurent Mazare2023-08-141-4/+1
* Optimize the logit computations in the whisper example. (#434)Laurent Mazare2023-08-132-29/+26
* Support longer sequences in language detection. (#428)Laurent Mazare2023-08-131-1/+3
* More accelerate optimizations (#427)Laurent Mazare2023-08-132-6/+25
* Add a KV cache to whisper. (#426)Laurent Mazare2023-08-123-24/+63
* Add a -language argument. (#425)Laurent Mazare2023-08-121-5/+15
* More multilingual support for whisper. (#419)Laurent Mazare2023-08-123-23/+47
* Basic multilingual support for whisper (#417)Laurent Mazare2023-08-122-13/+175
* Add more whisper variants. (#413)Laurent Mazare2023-08-111-3/+25
* Add some tracing to the whisper example. (#375)Laurent Mazare2023-08-092-45/+75
* Embed the mel filters in the whisper binary. (#373)Laurent Mazare2023-08-092-13/+4
* Softmax numerical stability. (#267)Laurent Mazare2023-07-282-9/+6
* Upgrading hf-hub to `0.2.0` (Modified API to not pass the Repo aroundNicolas Patry2023-07-271-12/+7
* Micro-cleanup. (#256)Laurent Mazare2023-07-271-4/+2
* Rename the .r functions to .dims so as to be a bit more explicit. (#220)Laurent Mazare2023-07-222-5/+5
* Merge branch 'main' into remove_wrapperNicolas Patry2023-07-191-1/+1
|\
| * Removing `candle-hub` internal to extract into `hf-hub` standalone.Nicolas Patry2023-07-191-1/+1
* | [Proposal] Remove SafeTensor wrapper (allows finer control for users).Nicolas Patry2023-07-191-2/+2
|/
* Add some 'cuda-if-available' helper function. (#172)Laurent Mazare2023-07-151-15/+1
* Removing cuda default.Nicolas Patry2023-07-141-1/+11
* Tensor mutability (#154)Laurent Mazare2023-07-131-1/+1
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-15 00:58:21 +0000