Upload 6 files

README.md

@@ -0,0 +1,79 @@
+---
+language:
+  - en
+tags:
+  - audio
+  - automatic-speech-recognition
+license: mit
+library_name: ctranslate2
+---
+
+# Distil-Whisper: Distil-Large-v3.5 for CTranslate2
+
+This repository contains the model weights for [distil-large-v3.5](https://huggingface.co/distil-whisper/distil-large-v3.5)
+converted to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format. CTranslate2 is a fast inference engine for 
+Transformer models and is the supported backend for the [Faster-Whisper](https://github.com/systran/faster-whisper) package.
+
+## Usage
+
+To use the model in Faster-Whisper, first install the PyPi package according to the [official instructions](https://github.com/SYSTRAN/faster-whisper#installation).
+
+For this example, we'll also install 🤗 Datasets to load a toy audio dataset from the Hugging Face Hub:
+
+```bash
+pip install --upgrade pip
+pip install --upgrade git+https://github.com/SYSTRAN/faster-whisper datasets[audio]
+```
+
+The following code snippet loads the distil-large-v3 model and runs inference on an example file from the LibriSpeech ASR
+dataset:
+
+```python
+import torch
+from faster_whisper import WhisperModel
+from datasets import load_dataset
+
+# define our torch configuration
+device = "cuda" if torch.cuda.is_available() else "cpu"
+compute_type = "float16" if torch.cuda.is_available() else "float32"
+
+# load model on GPU if available, else cpu
+model = WhisperModel("distil-whisper/distil-large-v3.5-ct2", device=device, compute_type=compute_type)
+
+# load toy dataset for example
+dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+sample = dataset[1]["audio"]["path"]
+
+segments, info = model.transcribe(sample, beam_size=5, language="en")
+
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+To transcribe a local audio file, simply pass the path to the audio file as the `audio` argument to transcribe:
+
+```python
+segments, info = model.transcribe("audio.mp3", beam_size=5, language="en")
+```
+
+## Model Details
+
+For more information about the Distil-Large-v3.5 model, refer to the original [model card](https://huggingface.co/distil-whisper/distil-large-v3.5).
+
+## License
+
+Distil-Whisper inherits the [MIT license](https://github.com/huggingface/distil-whisper/blob/main/LICENSE) from OpenAI's Whisper model.
+
+## Citation
+
+If you use this model, please consider citing the [Distil-Whisper paper](https://arxiv.org/abs/2311.00430):
+```
+@misc{gandhi2023distilwhisper,
+      title={Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling}, 
+      author={Sanchit Gandhi and Patrick von Platen and Alexander M. Rush},
+      year={2023},
+      eprint={2311.00430},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,280 @@
+{
+  "alignment_heads": [
+    [
+      1,
+      0
+    ],
+    [
+      1,
+      1
+    ],
+    [
+      1,
+      2
+    ],
+    [
+      1,
+      3
+    ],
+    [
+      1,
+      4
+    ],
+    [
+      1,
+      5
+    ],
+    [
+      1,
+      6
+    ],
+    [
+      1,
+      7
+    ],
+    [
+      1,
+      8
+    ],
+    [
+      1,
+      9
+    ],
+    [
+      1,
+      10
+    ],
+    [
+      1,
+      11
+    ],
+    [
+      1,
+      12
+    ],
+    [
+      1,
+      13
+    ],
+    [
+      1,
+      14
+    ],
+    [
+      1,
+      15
+    ],
+    [
+      1,
+      16
+    ],
+    [
+      1,
+      17
+    ],
+    [
+      1,
+      18
+    ],
+    [
+      1,
+      19
+    ]
+  ],
+  "lang_ids": [
+    50259,
+    50260,
+    50261,
+    50262,
+    50263,
+    50264,
+    50265,
+    50266,
+    50267,
+    50268,
+    50269,
+    50270,
+    50271,
+    50272,
+    50273,
+    50274,
+    50275,
+    50276,
+    50277,
+    50278,
+    50279,
+    50280,
+    50281,
+    50282,
+    50283,
+    50284,
+    50285,
+    50286,
+    50287,
+    50288,
+    50289,
+    50290,
+    50291,
+    50292,
+    50293,
+    50294,
+    50295,
+    50296,
+    50297,
+    50298,
+    50299,
+    50300,
+    50301,
+    50302,
+    50303,
+    50304,
+    50305,
+    50306,
+    50307,
+    50308,
+    50309,
+    50310,
+    50311,
+    50312,
+    50313,
+    50314,
+    50315,
+    50316,
+    50317,
+    50318,
+    50319,
+    50320,
+    50321,
+    50322,
+    50323,
+    50324,
+    50325,
+    50326,
+    50327,
+    50328,
+    50329,
+    50330,
+    50331,
+    50332,
+    50333,
+    50334,
+    50335,
+    50336,
+    50337,
+    50338,
+    50339,
+    50340,
+    50341,
+    50342,
+    50343,
+    50344,
+    50345,
+    50346,
+    50347,
+    50348,
+    50349,
+    50350,
+    50351,
+    50352,
+    50353,
+    50354,
+    50355,
+    50356,
+    50357,
+    50358
+  ],
+  "suppress_ids": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58b88b8585ffcd2135fddaaf421ce72cb223b32edea70d156aed1dea319a119
+size 1512927867

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}