whisper large v3 turbo - ct2 int8 version

README.md

@@ -1,3 +1,78 @@
----
-license: mit
----
+# Whisper Large v3 Turbo - CTranslate2
+
+This is a CTranslate2-optimized version of OpenAI's Whisper Large v3 Turbo model for automatic speech recognition (ASR).
+
+## Model Description
+
+This model is a converted version of the original Whisper Large v3 Turbo model, optimized for inference using CTranslate2. CTranslate2 is a C++ and Python library for efficient inference with Transformer models, providing:
+
+- **Faster inference**: Optimized implementations of attention mechanisms and feed-forward networks
+- **Lower memory usage**: Quantization support and memory-efficient attention
+- **Better throughput**: Batching and parallel processing optimizations
+- **Cross-platform compatibility**: Support for CPU and GPU inference
+
+## Conversion
+
+This model has been converted using the following command:
+
+```bash
+ct2-transformers-converter --model openai/whisper-large-v3-turbo --output_dir whisper-large-v3-turbo-ct2-int8 --quantization int8 --copy_files tokenizer.json preprocessor_config.json
+```
+
+The conversion includes **int8 quantization**, which provides several benefits:
+
+- **Reduced disk space**: Significantly smaller model size compared to the original float32 version
+- **Lower memory consumption**: Requires less RAM during inference
+- **Maintained accuracy**: Minimal quality loss while providing substantial efficiency gains
+- **Faster loading**: Reduced time to load the model from disk
+
+## Original Model
+
+This model is based on OpenAI's Whisper Large v3 Turbo, which is a state-of-the-art automatic speech recognition model that:
+
+- Supports 99 languages
+- Provides high-quality transcription and translation
+- Features improved accuracy and speed compared to previous Whisper versions
+- Handles various audio conditions and accents
+
+## Usage
+
+To use this model, you'll need to install CTranslate2 and the appropriate Whisper integration (faster-whisper):
+
+```bash
+pip install ctranslate2 faster-whisper
+```
+
+```python
+from faster_whisper import WhisperModel
+
+model_size = "path/to/whisper-large-v3-turbo-ct2"
+model = WhisperModel(model_size, device="cpu", compute_type="int8")
+
+segments, info = model.transcribe("audio.wav", beam_size=5)
+
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+## Performance
+
+This CTranslate2 version provides significant performance improvements over the original PyTorch implementation:
+
+- Up to 4x faster inference
+- Reduced memory consumption
+- Support for quantization
+- Optimized for both CPU and GPU inference
+
+## Supported Languages
+
+Same as the original Whisper Large v3 Turbo:
+Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.
+
+## Model Card
+
+- **Developed by**: OpenAI (original), converted to CT2 format
+- **Model type**: Automatic Speech Recognition
+- **Language(s)**: Multilingual (99 languages)
+- **License**: MIT
+- **Model size**: Large (1550M parameters)

config.json

@@ -0,0 +1,224 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
+  "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 sha256:7482f978f9493b93b3d0bf68a148a1a62ca02547e8ee981358ff8ef2de8a9418
+size 814054531

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
+}