Upload folder using huggingface_hub

README.md

@@ -1,94 +1,20 @@
 ---
-library_name: transformers
-license: apache-2.0
-datasets:
-- ivrit-ai/crowd-transcribe-v5
-- ivrit-ai/crowd-recital-whisper-training
-- ivrit-ai/knesset-plenums-whisper-training
-language:
-- he
-metrics:
-- wer
-base_model:
-- openai/whisper-large-v3
-pipeline_tag: automatic-speech-recognition
-tags:
-- mlx
+library_name: mlx
 ---
 
-# Model Card for Model ID
+# ivrit-ai-whisper-large-v3-mlx
+This model was converted to MLX format from [`ivrit-ai/whisper-large-v3`]().
 
-This model is a Hebrew finetune (continued training) of the OpenAI Whisper Large v3 model.
+## Use with mlx
+```bash
+pip install mlx-whisper
+```
 
+```python
+import mlx_whisper
 
-## Model Details
-
-### Model Description
-
-- **Developed by:** ivrit-ai
-- **Language(s) (NLP):** Hebrew
-- **License:** Apache-2.0
-- **Finetuned from model** openai/whisper-large-v3
-- **Training Date** Apr 2025
-
-## Bias, Risks, and Limitations
-
-Language detection capability of this model has been degraded during training - it is intended for mostly-hebrew audio transcription.
-Language token should be explicitly set to Hebrew.
-
-Additionally, the tanslation task was not trained and also degraded. This model would not be able to translate in any reasonable capacity.
-
-## How to Get Started with the Model
-
-Please follow the original [model card](https://huggingface.co/openai/whisper-large-v3#usage) for usage details - replacing with this model name.
-You can also fine other weight formats ad quantizations on the [ivrit ai](https://huggingface.co/ivrit-ai) HF page.
-
-We created some simple example scripts using this model and weights for other inference runtimes.
-Find those in the ["examples"](https://github.com/ivrit-ai/asr-training/tree/master/examples) folder within the training GitHub repo.
-
-## Training Details
-
-### Training Data
-
-This model was trained on the following datasets:
-
-- [ivrit-ai/crowd-transcribe-v5](https://huggingface.co/datasets/ivrit-ai/crowd-transcribe-v5) - Publicly accessible audio sources have been crowd-transcribed segment-by-segment - ~300h
-- [ivrit-ai/crowd-recital-whisper-training](https://huggingface.co/datasets/ivrit-ai/crowd-recital-whisper-training) - Crowd-sourced recording of Wikipedia article snippets. ~50h
-- [ivrit-ai/knesset-plenums-whisper-training](https://huggingface.co/datasets/ivrit-ai/knesset-plenums-whisper-training) - A subset of a Knesset (Israeli house of representatives) plenum protocols. ~4700h
-
-### Training Procedure
-
-This model was trained in two main phases:
-- Knesset based pre-training - over all ~4700h of data - 3 epochs, ~54h run
-- Mixed post-training over all crowd-transcribe-v5 (300h), crowd-recital-whisper-training (50h) and highest-quality filtered knessets data (150h) - 1 epoch
- - Interleaving of datasets with sampling probs: (0.9, 0.025, 0.075) respectively
- - Note that crowd-transcribe-v5 has about 5x shorter samples on average thus the over-sampling.
-
-This model is a weighted-average of the 3 lowest eval loss checkpoints from the same training run.
-Training code can be found on the ivrit-ai Github [here](https://github.com/ivrit-ai/asr-training)
-
-#### Preprocessing
-
-The "Crowd Recital" and "Knesset" datasets contain timestamps and previous text following the Whisper expected inputs.
-Timestamps were used from 40% of samples from those datasets, and 50% of the previous text was used.
-
-The "Crowd Transcribe" datasets has no timestamps or previous text and this preprocessing only included melspec feature extraction and text encoding.
-
-Preprocessing code can be found within the training code [repository](https://github.com/ivrit-ai/asr-training).
-
-Datasets were interleaved with 0.15:0.8:0.05 ratio (knesset:crowd-transcribe:crowd-recital).
-
-#### Training Hyperparameters
-
-- **Training regime:** bf16 mixed precision with sdpa
-- **Learning Rate:** 1e-5, Linear decay, 800 steps warmup for 3 epochs
-- **Batch Size:** 32
-
-#### Training Hardware / Duration
-
-- **GPU Type:** 8 x Nvidia A40 machine
-- **Duration:** ~60 run across both phases
-
-## Evaluation
-
-Please refer to the [ivrit-ai/hebrew-transcription-leaderboard](https://huggingface.co/spaces/ivrit-ai/hebrew-transcription-leaderboard)
+result = mlx_whisper.transcribe(
+    "FILE_NAME",
+    path_or_hf_repo=mlx-community/ivrit-ai-whisper-large-v3-mlx,
+)
+```

config.json

@@ -0,0 +1,13 @@
+{
+    "n_mels": 128,
+    "n_audio_ctx": 1500,
+    "n_audio_state": 1280,
+    "n_audio_head": 20,
+    "n_audio_layer": 32,
+    "n_vocab": 51866,
+    "n_text_ctx": 448,
+    "n_text_state": 1280,
+    "n_text_head": 20,
+    "n_text_layer": 32,
+    "model_type": "whisper"
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b9d7b9df7cb669101a3b166f6b37bcfb3dbe1f20b74e8b6e2867019472ab93
+size 3083275629