Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+language:
+- sn
+tags:
+- automatic-speech-recognition
+- whisper
+- audio
+- multi-stage-finetuning
+model-index:
+- name: Whisper Small Shona - Verdi AI OS Stage 1c
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: google/fleurs + manassehzw/shona-bible-bdsc-aligned
+      type: google/fleurs
+      args: sn_zw
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 25.52
+pipeline_tag: automatic-speech-recognition
+library_name: transformers
+---
+
+# 🌾 Verdi AI OS: Whisper Small Shona ASR (Stage 1c Mastered Core)
+
+This repository hosts a completely standalone, fully compiled model optimized natively for the Shona language (`sn-ZW`).
+
+## 📊 Training Progression Metrics
+- **Stage 1a (FLEURS Baseline):** Baseline WER dropped to **37.15%**
+- **Stage 1b (Bible Chunk 1):** Dropped WER to **29.39%**
+- **Stage 1c (Bible Chunk 2 & 3 Increments):** Achieved new floor of **25.52%** WER.

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c90484a5b9a9d0d38566e61bdc4433c9c4ffbfa5265d284bb5f86fded36ce68
+oid sha256:fc84ee09fa53767876dc4c0309a5f716a93ec3e6ec85bf298a5983ce8850dda0
 size 966995080

processor_config.json

@@ -0,0 +1,17 @@
+{
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "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,
+    "return_attention_mask": false,
+    "sampling_rate": 16000
+  },
+  "processor_class": "WhisperProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,128 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "is_local": false,
+  "language": null,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "predict_timestamps": false,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "task": null,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}