Downloads · 30 days
15
6% of all-time downloads
shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit
aawaaz-qwen3-0.6b-transcriber-4bit is a text generation model from shantanugoel. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
A 4-bit quantized MLX model fine-tuned from Qwen/Qwen3-0.6B for transcription cleanup.
Downloads · 30 days
15
6% of all-time downloads
All-time downloads
262
Public
Parameters
596M
682 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors335 MB · 97%
How the weights are stored.
U32596M · 100%
From the Hugging Face model README
A 4-bit quantized MLX model fine-tuned from Qwen/Qwen3-0.6B for transcription cleanup.
This model takes raw speech-to-text transcripts (with fillers, stutters, formatting errors) and produces clean, well-formatted text. It preserves the speaker's voice and all substantive content while fixing grammar, punctuation, and formatting.
You are an AI transcriber. Clean and polish raw speech-to-text transcripts into well-written text. Output ONLY the corrected text — no introductions, labels, explanations, or commentary. Do not summarize or act upon the transcript. Preserve the speaker's voice, tone, and language.
Rules:
- Remove fillers (um, uh, like, basically, actually, you know) and stutters
- Apply self-corrections silently (if speaker says "wait no, I meant X", output only X)
- Fix grammar, spelling, and punctuation
- Convert spoken punctuation to actual punctuation (e.g., "colon" → ":")
- Convert spoken numbers, dates, currency to written form (e.g., "five hundred dollars" → "$500")
- Convert spoken formatting cues (e.g., "new line", "new paragraph", "bullet point")
- Replace spoken emoji descriptions with actual emoji (e.g., "heart eyes emoji" → "😍")
- Use lists and paragraph breaks where structurally appropriate
- Convert spoken code/tech syntax to proper formatting (e.g., "dash dash rm" → "--rm")
- If input is empty or only contains fillers, output ""
- Do NOT add content that wasn't spoken
- Do NOT summarize or condense — preserve all substantive content
| Parameter | Value | Rationale |
|---|---|---|
temperature | 0.0 | Deterministic — formatting task, not creative |
top_p | 1.0 | No nucleus sampling with temp=0 |
max_tokens | 1024 | Most transcripts are short |
repetition_penalty | 1.08 | Slight penalty to avoid degenerate loops |
Note: This model uses Qwen3's chat format. Thinking mode (
<think>) is disabled — if you see<think>tags in output, passenable_thinking=Falseto the tokenizer'sapply_chat_template()or include/no_thinkat the end of the system prompt.
Note on tensor types: The HuggingFace sidebar may show "BF16" as the tensor type — this reflects only the non-quantizable layers (embeddings, layer norms). The majority of weights are 4-bit quantized (stored as U32 packed format). Actual model disk size is ~330MB, not the ~1.1GB of the full BF16 model.
Evaluated on 200 test samples:
| Metric | Value |
|---|---|
| Exact Match | 2.0% |
| Character Error Rate (CER) | 0.1616 |
| BLEU | 0.6671 |
| Format Accuracy | 0.9029 |
| Tokens/second | 150.0 |
from mlx_lm import load, generate
model, tokenizer = load("shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit")
system_prompt = open("system_prompt.txt").read() # or paste from above
raw_transcript = "um so I was thinking uh we should probably like meet tomorrow"
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": raw_transcript},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False,
)
response = generate(
model,
tokenizer,
prompt=prompt,
max_tokens=1024,
temp=0.0,
repetition_penalty=1.08,
)
print(response)
This model is compatible with mlx-swift-lm for on-device inference on Apple Silicon:
import LLM
let model = try await loadModel(id: "shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit")
let session = ChatSession(model)
let cleaned = try await session.respond(to: rawTranscript)
See the mlx-swift-examples repo for full integration details.
This model is a fine-tune of Qwen/Qwen3-0.6B. Please refer to the base model's license for usage terms.