Quantizated models added

fp16/README.md

@@ -0,0 +1,45 @@
+---
+language:
+  - hu
+tags:
+  - audio
+  - automatic-speech-recognition
+datasets:
+- mozilla-foundation/common_voice_16_0
+base_model: openai/whisper-small
+license: mit
+library_name: ctranslate2
+---
+
+# Whisper small model for CTranslate2
+
+This repository contains the conversion of a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format. Fine-tune is made by [@sarpba](https://huggingface.co/sarpba) on the Common Voice 16 dataset of Mozilla Foundation.
+
+This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper).
+
+## Example
+
+```python
+from faster_whisper import WhisperModel
+
+model = WhisperModel("small")
+
+segments, info = model.transcribe("audio.mp3")
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+## Conversion details
+
+The original model was converted with the following command:
+
+```
+ct2-transformers-converter --model Hungarians/whisper-small-cv16-hu --output_dir faster-whisper-small-cv16-fp16.hu \
+    --quantization fp16 --low_cpu_mem_usage --copy_files tokenizer_config.json preprocessor_config.json
+```
+
+Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
+
+## More information
+
+**For more information about the original model, see its [model card](https://huggingface.co/Hungarians/whisper-small-cv16-hu).**

fp16/config.json

@@ -0,0 +1,485 @@
+{
+  "alignment_heads": [
+    [
+      6,
+      0
+    ],
+    [
+      6,
+      1
+    ],
+    [
+      6,
+      2
+    ],
+    [
+      6,
+      3
+    ],
+    [
+      6,
+      4
+    ],
+    [
+      6,
+      5
+    ],
+    [
+      6,
+      6
+    ],
+    [
+      6,
+      7
+    ],
+    [
+      6,
+      8
+    ],
+    [
+      6,
+      9
+    ],
+    [
+      6,
+      10
+    ],
+    [
+      6,
+      11
+    ],
+    [
+      7,
+      0
+    ],
+    [
+      7,
+      1
+    ],
+    [
+      7,
+      2
+    ],
+    [
+      7,
+      3
+    ],
+    [
+      7,
+      4
+    ],
+    [
+      7,
+      5
+    ],
+    [
+      7,
+      6
+    ],
+    [
+      7,
+      7
+    ],
+    [
+      7,
+      8
+    ],
+    [
+      7,
+      9
+    ],
+    [
+      7,
+      10
+    ],
+    [
+      7,
+      11
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      1
+    ],
+    [
+      8,
+      2
+    ],
+    [
+      8,
+      3
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      5
+    ],
+    [
+      8,
+      6
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      8,
+      9
+    ],
+    [
+      8,
+      10
+    ],
+    [
+      8,
+      11
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      1
+    ],
+    [
+      9,
+      2
+    ],
+    [
+      9,
+      3
+    ],
+    [
+      9,
+      4
+    ],
+    [
+      9,
+      5
+    ],
+    [
+      9,
+      6
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      8
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      9,
+      10
+    ],
+    [
+      9,
+      11
+    ],
+    [
+      10,
+      0
+    ],
+    [
+      10,
+      1
+    ],
+    [
+      10,
+      2
+    ],
+    [
+      10,
+      3
+    ],
+    [
+      10,
+      4
+    ],
+    [
+      10,
+      5
+    ],
+    [
+      10,
+      6
+    ],
+    [
+      10,
+      7
+    ],
+    [
+      10,
+      8
+    ],
+    [
+      10,
+      9
+    ],
+    [
+      10,
+      10
+    ],
+    [
+      10,
+      11
+    ],
+    [
+      11,
+      0
+    ],
+    [
+      11,
+      1
+    ],
+    [
+      11,
+      2
+    ],
+    [
+      11,
+      3
+    ],
+    [
+      11,
+      4
+    ],
+    [
+      11,
+      5
+    ],
+    [
+      11,
+      6
+    ],
+    [
+      11,
+      7
+    ],
+    [
+      11,
+      8
+    ],
+    [
+      11,
+      9
+    ],
+    [
+      11,
+      10
+    ],
+    [
+      11,
+      11
+    ]
+  ],
+  "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
+  ],
+  "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,
+    50360,
+    50361,
+    50362
+  ],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

fp16/hash.json

@@ -0,0 +1,10 @@
+{
+  "README.md": "7fa4402e90a36ea3c3c5546d6e94a652",
+  "config.json": "72c97d7fb45f7a607145d121b718ee65",
+  "model.bin": "3b0927dcce933b1d86300ab3cb5bca78",
+  "preprocessor_config.json": "15d1d7ee1cc6801b71f8ab68966aed86",
+  "tokenizer_config.json": "ea5ff3bfa7553fabbfbcb02846302bbc",
+  "vocabulary.json": "aebe7623626c8f3f61cc5208ff29c348",
+  "vocabulary.txt": "980d7011195d0c733bd374e31708717f",
+  "hash.json": "d41d8cd98f00b204e9800998ecf8427e"
+}

fp16/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03995062195aade7640ead072fa81cea85948077e0e7d7d8da3866ff79c532a
+size 483546977

fp16/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}

fp32/README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- hf-asr-leaderboard
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_16_0
+language:
+- hu
+widget:
+- example_title: Sample 1
+  src: https://huggingface.co/datasets/Hungarians/samples/resolve/main/Sample1.flac
+- example_title: Sample 2
+  src: https://huggingface.co/datasets/Hungarians/samples/resolve/main/Sample2.flac
+metrics:
+- wer
+pipeline_tag: automatic-speech-recognition
+model-index:
+- name: Whisper Small Hungarian
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 16.0 - Hungarian
+      type: mozilla-foundation/common_voice_16_0
+      config: hu
+      split: test
+      args: hu
+    metrics:
+    - name: Wer
+      type: wer
+      value: 18.8314
+      verified: true
+
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Whisper Small Hungarian (training in progress)
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16 dataset of Mozilla Foundation.
+It achieves the following results on the evaluation set:
+
+Tempolary at step 3500: 
+
+- Wer: 18.8314
+
+Unfortunatly the colab disconected, this is the end... :( maybe later continue
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.25e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 400
+- planed training_steps: 6000
+- executed steps: 3500 only (colab dc)
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Steps | Training Loss | Validation Loss | Wer Ortho |    Wer    |
+|:-----:|:-------------:|:---------------:|:---------:|:---------:|
+| 500	|   0.354600    |    0.349688     |	34.385555 |	31.246555 |
+| 1000	|   0.283800	|    0.290485	  | 29.696507 |	26.625776 |
+| 1500	|   0.248800	|    0.255122	  | 26.360826 |	23.300925 |
+| 2000	|   0.198300	|    0.234539	  | 24.557530 |	21.714145 |
+| 2500	|   0.196300    |    0.224310	  | 23.557423 |	20.698512 |
+| 3000	|   0.153000	|    0.210894	  | 22.088291 |	19.231356 |
+| 3500	|   0.109100	|    0.210817	  | 21.465313 |	18.831435 |
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

fp32/config.json

@@ -0,0 +1,152 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [
+    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,
+    50360,
+    50361,
+    50362
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

fp32/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}

int8/README.md

@@ -0,0 +1,45 @@
+---
+language:
+  - hu
+tags:
+  - audio
+  - automatic-speech-recognition
+datasets:
+- mozilla-foundation/common_voice_16_0
+base_model: openai/whisper-small
+license: mit
+library_name: ctranslate2
+---
+
+# Whisper small model for CTranslate2
+
+This repository contains the conversion of a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format. Fine-tune is made by [@sarpba](https://huggingface.co/sarpba) on the Common Voice 16 dataset of Mozilla Foundation.
+
+This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/systran/faster-whisper).
+
+## Example
+
+```python
+from faster_whisper import WhisperModel
+
+model = WhisperModel("small")
+
+segments, info = model.transcribe("audio.mp3")
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+## Conversion details
+
+The original model was converted with the following command:
+
+```
+ct2-transformers-converter --model Hungarians/whisper-small-cv16-hu --output_dir faster-whisper-small-cv16-int8.hu \
+    --quantization int8 --low_cpu_mem_usage --copy_files tokenizer_config.json preprocessor_config.json
+```
+
+Note that the model weights are saved in INT8. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
+
+## More information
+
+**For more information about the original model, see its [model card](https://huggingface.co/Hungarians/whisper-small-cv16-hu).**

int8/config.json

@@ -0,0 +1,485 @@
+{
+  "alignment_heads": [
+    [
+      6,
+      0
+    ],
+    [
+      6,
+      1
+    ],
+    [
+      6,
+      2
+    ],
+    [
+      6,
+      3
+    ],
+    [
+      6,
+      4
+    ],
+    [
+      6,
+      5
+    ],
+    [
+      6,
+      6
+    ],
+    [
+      6,
+      7
+    ],
+    [
+      6,
+      8
+    ],
+    [
+      6,
+      9
+    ],
+    [
+      6,
+      10
+    ],
+    [
+      6,
+      11
+    ],
+    [
+      7,
+      0
+    ],
+    [
+      7,
+      1
+    ],
+    [
+      7,
+      2
+    ],
+    [
+      7,
+      3
+    ],
+    [
+      7,
+      4
+    ],
+    [
+      7,
+      5
+    ],
+    [
+      7,
+      6
+    ],
+    [
+      7,
+      7
+    ],
+    [
+      7,
+      8
+    ],
+    [
+      7,
+      9
+    ],
+    [
+      7,
+      10
+    ],
+    [
+      7,
+      11
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      1
+    ],
+    [
+      8,
+      2
+    ],
+    [
+      8,
+      3
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      5
+    ],
+    [
+      8,
+      6
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      8,
+      9
+    ],
+    [
+      8,
+      10
+    ],
+    [
+      8,
+      11
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      1
+    ],
+    [
+      9,
+      2
+    ],
+    [
+      9,
+      3
+    ],
+    [
+      9,
+      4
+    ],
+    [
+      9,
+      5
+    ],
+    [
+      9,
+      6
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      8
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      9,
+      10
+    ],
+    [
+      9,
+      11
+    ],
+    [
+      10,
+      0
+    ],
+    [
+      10,
+      1
+    ],
+    [
+      10,
+      2
+    ],
+    [
+      10,
+      3
+    ],
+    [
+      10,
+      4
+    ],
+    [
+      10,
+      5
+    ],
+    [
+      10,
+      6
+    ],
+    [
+      10,
+      7
+    ],
+    [
+      10,
+      8
+    ],
+    [
+      10,
+      9
+    ],
+    [
+      10,
+      10
+    ],
+    [
+      10,
+      11
+    ],
+    [
+      11,
+      0
+    ],
+    [
+      11,
+      1
+    ],
+    [
+      11,
+      2
+    ],
+    [
+      11,
+      3
+    ],
+    [
+      11,
+      4
+    ],
+    [
+      11,
+      5
+    ],
+    [
+      11,
+      6
+    ],
+    [
+      11,
+      7
+    ],
+    [
+      11,
+      8
+    ],
+    [
+      11,
+      9
+    ],
+    [
+      11,
+      10
+    ],
+    [
+      11,
+      11
+    ]
+  ],
+  "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
+  ],
+  "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,
+    50360,
+    50361,
+    50362
+  ],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

int8/hash.json

@@ -0,0 +1,10 @@
+{
+  "README.md": "4ff5ec2d9bc1f17efa15deee2206b5b9",
+  "config.json": "72c97d7fb45f7a607145d121b718ee65",
+  "model.bin": "2f4b4f3e055a34987ea2883995976e76",
+  "preprocessor_config.json": "15d1d7ee1cc6801b71f8ab68966aed86",
+  "tokenizer_config.json": "ea5ff3bfa7553fabbfbcb02846302bbc",
+  "vocabulary.json": "aebe7623626c8f3f61cc5208ff29c348",
+  "vocabulary.txt": "980d7011195d0c733bd374e31708717f",
+  "hash.json": "d41d8cd98f00b204e9800998ecf8427e"
+}

int8/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dd343cc0e9e5c322bbaadddfdb50a9e2324e393eb6dcca38e72a01b75ca6fa
+size 254058951

int8/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}