update model

vegam-whisper-medium-ml-fp16/.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

vegam-whisper-medium-ml-fp16/00b38e80-80b8-4f70-babf-566e848879fc.webm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99eae55e0bcccca47e10318859986878c47a34d8f1c601c638e70a0b97d77cf
+size 31241

vegam-whisper-medium-ml-fp16/README.md

@@ -0,0 +1,97 @@
+---
+language:
+- ml
+tags:
+- audio
+- automatic-speech-recognition
+license: mit
+datasets:
+- google/fleurs
+- thennal/IMaSC
+- mozilla-foundation/common_voice_11_0
+library_name: ctranslate2
+---
+
+# vegam-whipser-medium-ml 
+
+This is a conversion of [thennal/whisper-medium-ml](https://huggingface.co/thennal/whisper-medium-ml) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
+
+This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/guillaumekln/faster-whisper).
+
+## Installation
+
+- Install [faster-whisper](https://github.com/guillaumekln/faster-whisper). More details about installation can be [found here in faster-whisper](https://github.com/guillaumekln/faster-whisper/tree/master#installation).
+
+```
+pip install faster-whisper
+```
+
+- Install  [git-lfs](https://git-lfs.com/) for using this project. Note that git-lfs is just for downloading model from hugging-face.
+
+```
+apt-get install git-lfs
+```
+
+- Download the model weights
+
+```
+git lfs install
+git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml-fp16
+```
+
+## Usage
+
+```
+from faster_whisper import WhisperModel
+
+model_path = "vegam-whisper-medium-ml-fp16"
+
+# Run on GPU with FP16
+model = WhisperModel(model_path, device="cuda", compute_type="float16")
+
+segments, info = model.transcribe("audio.mp3", beam_size=5)
+
+print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
+
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+## Example
+
+```
+from faster_whisper import WhisperModel
+
+model_path = "vegam-whisper-medium-ml-fp16"
+
+model = WhisperModel(model_path, device="cuda", compute_type="float16")
+
+
+segments, info = model.transcribe("00b38e80-80b8-4f70-babf-566e848879fc.webm", beam_size=5)
+
+print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
+
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+```
+
+> Detected language 'ta' with probability 0.353516
+
+> [0.00s -> 4.74s] പാലം കടുക്കുവോളം നാരായണ പാലം കടന്നാലൊ കൂരായണ
+
+Note: The audio file [00b38e80-80b8-4f70-babf-566e848879fc.webm](https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml/blob/main/00b38e80-80b8-4f70-babf-566e848879fc.webm) is from [Malayalam Speech Corpus](https://blog.smc.org.in/malayalam-speech-corpus/) and is stored along with model weights.
+## Conversion Details
+
+This conversion was possible with wonderful [CTranslate2 library](https://github.com/OpenNMT/CTranslate2) leveraging the [Transformers converter for OpenAI Whisper](https://opennmt.net/CTranslate2/guides/transformers.html#whisper).The original model was converted with the following command:
+
+```
+ct2-transformers-converter --model thennal/whisper-medium-ml --output_dir vegam-whisper-medium-ml-fp16 \
+--quantization float16
+```
+
+## Many Thanks to
+
+- Creators of CTranslate2 and faster-whisper
+- Thennal D K
+- Santhosh Thottingal
+ 

vegam-whisper-medium-ml-fp16/config.json

@@ -0,0 +1,878 @@
+{
+  "alignment_heads": [
+    [
+      12,
+      0
+    ],
+    [
+      12,
+      1
+    ],
+    [
+      12,
+      2
+    ],
+    [
+      12,
+      3
+    ],
+    [
+      12,
+      4
+    ],
+    [
+      12,
+      5
+    ],
+    [
+      12,
+      6
+    ],
+    [
+      12,
+      7
+    ],
+    [
+      12,
+      8
+    ],
+    [
+      12,
+      9
+    ],
+    [
+      12,
+      10
+    ],
+    [
+      12,
+      11
+    ],
+    [
+      12,
+      12
+    ],
+    [
+      12,
+      13
+    ],
+    [
+      12,
+      14
+    ],
+    [
+      12,
+      15
+    ],
+    [
+      13,
+      0
+    ],
+    [
+      13,
+      1
+    ],
+    [
+      13,
+      2
+    ],
+    [
+      13,
+      3
+    ],
+    [
+      13,
+      4
+    ],
+    [
+      13,
+      5
+    ],
+    [
+      13,
+      6
+    ],
+    [
+      13,
+      7
+    ],
+    [
+      13,
+      8
+    ],
+    [
+      13,
+      9
+    ],
+    [
+      13,
+      10
+    ],
+    [
+      13,
+      11
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      13,
+      13
+    ],
+    [
+      13,
+      14
+    ],
+    [
+      13,
+      15
+    ],
+    [
+      14,
+      0
+    ],
+    [
+      14,
+      1
+    ],
+    [
+      14,
+      2
+    ],
+    [
+      14,
+      3
+    ],
+    [
+      14,
+      4
+    ],
+    [
+      14,
+      5
+    ],
+    [
+      14,
+      6
+    ],
+    [
+      14,
+      7
+    ],
+    [
+      14,
+      8
+    ],
+    [
+      14,
+      9
+    ],
+    [
+      14,
+      10
+    ],
+    [
+      14,
+      11
+    ],
+    [
+      14,
+      12
+    ],
+    [
+      14,
+      13
+    ],
+    [
+      14,
+      14
+    ],
+    [
+      14,
+      15
+    ],
+    [
+      15,
+      0
+    ],
+    [
+      15,
+      1
+    ],
+    [
+      15,
+      2
+    ],
+    [
+      15,
+      3
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      5
+    ],
+    [
+      15,
+      6
+    ],
+    [
+      15,
+      7
+    ],
+    [
+      15,
+      8
+    ],
+    [
+      15,
+      9
+    ],
+    [
+      15,
+      10
+    ],
+    [
+      15,
+      11
+    ],
+    [
+      15,
+      12
+    ],
+    [
+      15,
+      13
+    ],
+    [
+      15,
+      14
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      0
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      16,
+      2
+    ],
+    [
+      16,
+      3
+    ],
+    [
+      16,
+      4
+    ],
+    [
+      16,
+      5
+    ],
+    [
+      16,
+      6
+    ],
+    [
+      16,
+      7
+    ],
+    [
+      16,
+      8
+    ],
+    [
+      16,
+      9
+    ],
+    [
+      16,
+      10
+    ],
+    [
+      16,
+      11
+    ],
+    [
+      16,
+      12
+    ],
+    [
+      16,
+      13
+    ],
+    [
+      16,
+      14
+    ],
+    [
+      16,
+      15
+    ],
+    [
+      17,
+      0
+    ],
+    [
+      17,
+      1
+    ],
+    [
+      17,
+      2
+    ],
+    [
+      17,
+      3
+    ],
+    [
+      17,
+      4
+    ],
+    [
+      17,
+      5
+    ],
+    [
+      17,
+      6
+    ],
+    [
+      17,
+      7
+    ],
+    [
+      17,
+      8
+    ],
+    [
+      17,
+      9
+    ],
+    [
+      17,
+      10
+    ],
+    [
+      17,
+      11
+    ],
+    [
+      17,
+      12
+    ],
+    [
+      17,
+      13
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      17,
+      15
+    ],
+    [
+      18,
+      0
+    ],
+    [
+      18,
+      1
+    ],
+    [
+      18,
+      2
+    ],
+    [
+      18,
+      3
+    ],
+    [
+      18,
+      4
+    ],
+    [
+      18,
+      5
+    ],
+    [
+      18,
+      6
+    ],
+    [
+      18,
+      7
+    ],
+    [
+      18,
+      8
+    ],
+    [
+      18,
+      9
+    ],
+    [
+      18,
+      10
+    ],
+    [
+      18,
+      11
+    ],
+    [
+      18,
+      12
+    ],
+    [
+      18,
+      13
+    ],
+    [
+      18,
+      14
+    ],
+    [
+      18,
+      15
+    ],
+    [
+      19,
+      0
+    ],
+    [
+      19,
+      1
+    ],
+    [
+      19,
+      2
+    ],
+    [
+      19,
+      3
+    ],
+    [
+      19,
+      4
+    ],
+    [
+      19,
+      5
+    ],
+    [
+      19,
+      6
+    ],
+    [
+      19,
+      7
+    ],
+    [
+      19,
+      8
+    ],
+    [
+      19,
+      9
+    ],
+    [
+      19,
+      10
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      19,
+      12
+    ],
+    [
+      19,
+      13
+    ],
+    [
+      19,
+      14
+    ],
+    [
+      19,
+      15
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      20,
+      1
+    ],
+    [
+      20,
+      2
+    ],
+    [
+      20,
+      3
+    ],
+    [
+      20,
+      4
+    ],
+    [
+      20,
+      5
+    ],
+    [
+      20,
+      6
+    ],
+    [
+      20,
+      7
+    ],
+    [
+      20,
+      8
+    ],
+    [
+      20,
+      9
+    ],
+    [
+      20,
+      10
+    ],
+    [
+      20,
+      11
+    ],
+    [
+      20,
+      12
+    ],
+    [
+      20,
+      13
+    ],
+    [
+      20,
+      14
+    ],
+    [
+      20,
+      15
+    ],
+    [
+      21,
+      0
+    ],
+    [
+      21,
+      1
+    ],
+    [
+      21,
+      2
+    ],
+    [
+      21,
+      3
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      21,
+      5
+    ],
+    [
+      21,
+      6
+    ],
+    [
+      21,
+      7
+    ],
+    [
+      21,
+      8
+    ],
+    [
+      21,
+      9
+    ],
+    [
+      21,
+      10
+    ],
+    [
+      21,
+      11
+    ],
+    [
+      21,
+      12
+    ],
+    [
+      21,
+      13
+    ],
+    [
+      21,
+      14
+    ],
+    [
+      21,
+      15
+    ],
+    [
+      22,
+      0
+    ],
+    [
+      22,
+      1
+    ],
+    [
+      22,
+      2
+    ],
+    [
+      22,
+      3
+    ],
+    [
+      22,
+      4
+    ],
+    [
+      22,
+      5
+    ],
+    [
+      22,
+      6
+    ],
+    [
+      22,
+      7
+    ],
+    [
+      22,
+      8
+    ],
+    [
+      22,
+      9
+    ],
+    [
+      22,
+      10
+    ],
+    [
+      22,
+      11
+    ],
+    [
+      22,
+      12
+    ],
+    [
+      22,
+      13
+    ],
+    [
+      22,
+      14
+    ],
+    [
+      22,
+      15
+    ],
+    [
+      23,
+      0
+    ],
+    [
+      23,
+      1
+    ],
+    [
+      23,
+      2
+    ],
+    [
+      23,
+      3
+    ],
+    [
+      23,
+      4
+    ],
+    [
+      23,
+      5
+    ],
+    [
+      23,
+      6
+    ],
+    [
+      23,
+      7
+    ],
+    [
+      23,
+      8
+    ],
+    [
+      23,
+      9
+    ],
+    [
+      23,
+      10
+    ],
+    [
+      23,
+      11
+    ],
+    [
+      23,
+      12
+    ],
+    [
+      23,
+      13
+    ],
+    [
+      23,
+      14
+    ],
+    [
+      23,
+      15
+    ]
+  ],
+  "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": [],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

vegam-whisper-medium-ml-fp16/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f41cbe71f56faef31b5fd181e96b5f05add5cdcef83aec11480d15639ee5eb
+size 1527906378