Upload folder using huggingface_hub

Readme.md

@@ -0,0 +1,67 @@
+---
+language:
+  - ht
+tags:
+  - audio
+  - automatic-speech-recognition
+license: mit
+library_name: ctranslate2
+---
+
+# Whisper small model for CTranslate2
+
+This repository contains the conversion of [YassineKader/whisper-small-haitian](https://huggingface.co/YassineKader/whisper-small-haitian) 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).
+
+## Example
+
+```python
+import ctranslate2
+import librosa
+import transformers
+from datetime import datetime
+# Load and resample the audio file.
+audio, _ = librosa.load("audio1.wav", sr=16000, mono=True)
+# Compute the features of the first 30 seconds of audio.
+processor = transformers.WhisperProcessor.from_pretrained("YassineKader/whisper-small-haitian")
+inputs = processor(audio, return_tensors="np", sampling_rate=16000)
+features = ctranslate2.StorageView.from_array(inputs.input_features)
+# Load the model on CPU.
+model = ctranslate2.models.Whisper("whisper-small-HT")
+# Detect the language.
+results = model.detect_language(features)
+language, probability = results[0][0]
+print("Detected language %s with probability %f" % (language, probability))
+print(datetime.now())
+# Describe the task in the prompt.
+# See the prompt format in https://github.com/openai/whisper.
+prompt = processor.tokenizer.convert_tokens_to_ids(
+    [
+        "<|startoftranscript|>",
+        language,
+        "<|transcribe|>",
+        "<|notimestamps|>",  # Remove this token to generate timestamps.
+    ]
+)
+# Run generation for the 30-second window.
+results = model.generate(features, [prompt])
+transcription = processor.decode(results[0].sequences_ids[0])
+
+print(datetime.now())
+print(transcription)
+```
+
+## Conversion details
+
+The original model was converted with the following command:
+
+```
+ct2-transformers-converter --model guillaumekln/faster-whisper-small --output_dir faster-whisper-small-ht --copy_files tokenizer.json --quantization float32
+```
+
+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/openai/whisper-small).**

config.json

@@ -0,0 +1,398 @@
+{
+  "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": [],
+  "suppress_ids_begin": [
+    220,
+    50257
+  ]
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1491f3c41cd8a048ad9c845aae1181aa4ca2a4c8629748fe7eddb793267840c
+size 967072068