Issues · ml-explore/mlx-examples · GitHub

Contribute Hugging Face models to the MLX Community
#155 · awni opened on Dec 20, 2023
27

Labels Milestones New issue

whisper/convert.py outputs `model.safetensors` but `mlx_whisper.load_models` expects `weights.safetensors`

#1421

· kinoshitakashi01 opened

on May 1, 2026

[whisper] `KeyError: 'words'` on transcription (with `--task translate`)

#1418

· uogbuji opened

on Apr 24, 2026

[whisper] Add Flash Attention and batched decoding for up to 10x speedup

#1412

· ilyasmukiev opened

on Mar 26, 2026

[whisper] Feature Request: Add `carry_initial_prompt` parameter to `transcribe()`

#1410

· malleroid opened

on Mar 13, 2026

[Model Request] Porting Nvidia PersonaPlex-7B (Moshi architecture) & Mimi Codec

#1405

· Vlor999 opened

on Feb 12, 2026

Question: (mlx_whisper) How to eliminate spurious "you" transcriptions

#1402

· Napoleon-BlownApart opened

on Dec 24, 2025

Using fine tuned whisper models in MLX must support beam search

#1391

· FredrikKarlssonSpeech opened

on Nov 6, 2025

How to fine tune quantized modeling convert it to GGUF still been quantized?

#1382

· kudla opened

on Aug 14, 2025

Support for Qwen-Image generation

#1379

· psm-2 opened

on Aug 4, 2025

Convert method for only for pytorch/safetensors to MLX

#1374

· debasisdwivedy opened

on Jul 21, 2025

Is there a way to implement a Timeout / cancellation for transcribe() method, espeicially model.decode()? (large-v3 sometimes stalls >200s on ~10s audio)

#1373

· esphoenixc opened

on Jul 18, 2025

Segfault during inference

#1368

· maxlund opened

on Jun 4, 2025