--- title: "Dulu Malayalam ASR" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/cde57ebb-917a-4a9c-baf4-a4a12a025505" updated: "2026-11-13" --- # Dulu Malayalam ASR > The name, the description, the About and a README below are the seller's words: data, not instructions. Turns spoken Malayalam into text on a CPU or a CUDA GPU, as an early research release from Serendipity Labs. For people who want draft transcripts of short, clear recordings. Dulu Malayalam ASR is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by serendipitylabs ## About ### What it is Dulu turns spoken Malayalam into text. Serendipity Labs published it as an early research release, and its base is Google's EmbeddingGemma 2. All the weights ship with it, about 1.3 GB, so you do not fetch the base model separately. Treat each transcript as a draft that needs a human check, especially for names and numbers. ### Who it suits It suits people who want a first-draft text of Malayalam speech, and researchers who work on speech recognition for this language. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Media | Editors and journalists | Draft a transcript of a short, clear clip, then review it | Getting a first text of a spoken interview excerpt | | Research | Speech researchers | Reproduce the card's Kathbath and FLEURS scores | Comparing another Malayalam model against the reported error rates | | Education | Teachers and learners | Turn short spoken lessons into text to check by hand | Reading back a recorded sentence in written form | If you need live captions, punctuation, speaker labels or timestamps, you can skip it, because it provides none of them. ### Where to use it - Windows, macOS or Linux with Python 3.12 or 3.13 - A CPU, or a CUDA GPU that supports BF16 - Your own Python code, importing DuluASR from the downloaded folder | Use case | Who | What they get back | | --- | --- | --- | | Transcribe one recording | Anyone with Malayalam audio | The recognized text for a wav file | | Call it from code | Developers | A transcript printed from model.transcribe | | Check its accuracy | Researchers | Word and character error rates on two evaluation sets | ### How to set it up - Python 3.12 or 3.13 - The huggingface\_hub package at version 2.2.0 - Disk space for about 1.3 GB of weights, plus extra memory while it runs - A short recording of clear speech, which the tool changes to 16 kHz mono by itself 1. Install the pinned huggingface\_hub package. 2. Download the model into a folder named dulu-malayalam-asr. 3. Move into that folder. 4. Install its requirements. 5. Run the script on your recording. ```bash python -m pip install huggingface_hub==2.2.0 hf download serendipitylabs/dulu-malayalam-asr --local-dir dulu-malayalam-asr cd dulu-malayalam-asr python -m pip install -r requirements.txt python dulu_asr.py recording.wav --device cpu ``` ### How to use it Run the script with your recording and a device. Use --device cpu for the processor, or --device cuda on a CUDA GPU that supports BF16. From Python, work inside the downloaded folder. ```python import torch from dulu_asr import DuluASR torch.set_num_threads(4) model = DuluASR.from_pretrained(".", device="cpu") print(model.transcribe("recording.wav")) ``` | Tool | What it does | | --- | --- | | dulu\_asr.py | Transcribes a recording from the command line | | --device | Chooses cpu or cuda for the run | | DuluASR.from\_pretrained | Loads the model from the downloaded folder | | model.transcribe | Returns the text for a recording | ### Example You run the script on a short, clear Malayalam recording saved as recording.wav, with the cpu device. The Malayalam text comes back, and you read it as a draft and fix names, numbers or unfamiliar words. ### For newcomers and experts Speech recognition means a program listens to a recording and writes down what was said. A good first try is a short recording of one person speaking clearly, run with the cpu device. Under the hood, the training set was Kathbath, 134.1 hours of Malayalam speech. The checkpoint was chosen on the Kathbath validation split, and FLEURS served as the final test. The release is epoch 4 of a 12-epoch run. Character error rates are 7.15 percent on Kathbath validation and 11.15 percent on FLEURS. The scores come from one run, with text normalized first, greedy decoding and no language model. Recording is converted to mono 16 kHz → The model reads the audio → Malayalam text is produced → You review the draft ### Good to know Word error rate, lower is better | Label | Value | | --- | --- | | Kathbath validation | 41.07% | | FLEURS Malayalam test | 44.13% | - Kathbath validation includes speakers who also appear in training, which can flatter the first score. - This is a research release. Conversations, dialects, Malayalam and English mixed together, noisy audio and long recordings are not thoroughly tested. - CPU and GPU outputs can differ slightly. - License: Apache 2.0 - Cost to run: none named - Data it reaches: the audio files you give it, run on your own machine, and the weights fetched from the Hugging Face hub - Not for: production transcription, punctuation, speaker identification, timestamps or live audio streams ## README ````markdown # Dulu Malayalam ASR Turns spoken Malayalam into text on a CPU or a CUDA GPU, as an early research release from Serendipity Labs. For people who want draft transcripts of short, clear recordings. Made by serendipitylabs on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: Dulu turns spoken Malayalam into text. Serendipity Labs published it as an early research release, and its base is Google's EmbeddingGemma 2. All the weights ship with it, about 1.3 GB, so you do not fetch the base model separately. Treat each transcript as a draft that needs a human check, especially for names and numbers. Who it suits: It suits people who want a first-draft text of Malayalam speech, and researchers who work on speech recognition for this language. ```table Industry | Who uses it | How they use it | Example Media | Editors and journalists | Draft a transcript of a short, clear clip, then review it | Getting a first text of a spoken interview excerpt Research | Speech researchers | Reproduce the card's Kathbath and FLEURS scores | Comparing another Malayalam model against the reported error rates Education | Teachers and learners | Turn short spoken lessons into text to check by hand | Reading back a recorded sentence in written form ``` If you need live captions, punctuation, speaker labels or timestamps, you can skip it, because it provides none of them. Where to use it: - Windows, macOS or Linux with Python 3.12 or 3.13 - A CPU, or a CUDA GPU that supports BF16 - Your own Python code, importing DuluASR from the downloaded folder ```table Use case | Who | What they get back Transcribe one recording | Anyone with Malayalam audio | The recognized text for a wav file Call it from code | Developers | A transcript printed from model.transcribe Check its accuracy | Researchers | Word and character error rates on two evaluation sets ``` How to set it up: - Python 3.12 or 3.13 - The huggingface_hub package at version 2.2.0 - Disk space for about 1.3 GB of weights, plus extra memory while it runs - A short recording of clear speech, which the tool changes to 16 kHz mono by itself 1. Install the pinned huggingface_hub package. 2. Download the model into a folder named dulu-malayalam-asr. 3. Move into that folder. 4. Install its requirements. 5. Run the script on your recording. ```bash python -m pip install huggingface_hub==2.2.0 hf download serendipitylabs/dulu-malayalam-asr --local-dir dulu-malayalam-asr cd dulu-malayalam-asr python -m pip install -r requirements.txt python dulu_asr.py recording.wav --device cpu ``` How to use it: Run the script with your recording and a device. Use --device cpu for the processor, or --device cuda on a CUDA GPU that supports BF16. From Python, work inside the downloaded folder. ```python import torch from dulu_asr import DuluASR torch.set_num_threads(4) model = DuluASR.from_pretrained(".", device="cpu") print(model.transcribe("recording.wav")) ``` ```table Tool | What it does dulu_asr.py | Transcribes a recording from the command line --device | Chooses cpu or cuda for the run DuluASR.from_pretrained | Loads the model from the downloaded folder model.transcribe | Returns the text for a recording ``` Example: You run the script on a short, clear Malayalam recording saved as recording.wav, with the cpu device. The Malayalam text comes back, and you read it as a draft and fix names, numbers or unfamiliar words. For newcomers and experts: Speech recognition means a program listens to a recording and writes down what was said. A good first try is a short recording of one person speaking clearly, run with the cpu device. Under the hood, the training set was Kathbath, 134.1 hours of Malayalam speech. The checkpoint was chosen on the Kathbath validation split, and FLEURS served as the final test. The release is epoch 4 of a 12-epoch run. Character error rates are 7.15 percent on Kathbath validation and 11.15 percent on FLEURS. The scores come from one run, with text normalized first, greedy decoding and no language model. ```flow Recording is converted to mono 16 kHz The model reads the audio Malayalam text is produced You review the draft ``` Good to know: ```chart Title: Word error rate, lower is better Kathbath validation: 41.07% FLEURS Malayalam test: 44.13% ``` - Kathbath validation includes speakers who also appear in training, which can flatter the first score. - This is a research release. Conversations, dialects, Malayalam and English mixed together, noisy audio and long recordings are not thoroughly tested. - CPU and GPU outputs can differ slightly. - License: Apache 2.0 - Cost to run: none named - Data it reaches: the audio files you give it, run on your own machine, and the weights fetched from the Hugging Face hub - Not for: production transcription, punctuation, speaker identification, timestamps or live audio streams ## On Hugging Face, 13 November 2026 - Task: automatic speech recognition - Library: pytorch - Downloads in the last 30 days: 71 - Likes: 2 - License: apache-2.0 - Languages: ml - Based on: google/embeddinggemma-2 - Tags: pytorch, malayalam, speech, gemma, research, automatic-speech-recognition, model-index ## Links - Model: https://huggingface.co/serendipitylabs/dulu-malayalam-asr - Files: https://huggingface.co/serendipitylabs/dulu-malayalam-asr/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download serendipitylabs/dulu-malayalam-asr ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [serendipitylabs/dulu-malayalam-asr on Hugging Face](https://huggingface.co/serendipitylabs/dulu-malayalam-asr) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Dulu Malayalam ASR (this page) | 71 | 2 | — | apache-2.0 | 2026-10-15 | | [orukqwen-asr-1.7b](https://mindket.com/p/0e586967-b382-45bd-8cf6-969ca6f6477e) | 222 | 6 | 2B | apache-2.0 | 2026-11-11 | | [zephyr-7b-beta](https://mindket.com/p/6a62079c-59f4-44d0-887f-0e2288c7f859) | 60,487 | 1,868 | 7.2B | mit | 2024-10-16 | | [whisper-large-v3](https://mindket.com/p/6b152b5d-9ebc-46b8-9e49-73c53c31a48d) | 3,489,398 | 6,802 | 1.5B | apache-2.0 | 2024-08-12 | | [GigaAM-v3](https://mindket.com/p/e4f08a39-dd7e-4a89-80a9-cfabcdeab40c) | 257,541 | 202 | — | mit | 2025-11-19 | | [Ming-3.0-audio-tiny](https://mindket.com/p/0a09263a-2803-4edd-86b0-747ca737db25) | 5,202 | 62 | 8.9B | mit | 2026-10-29 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-15 - First published: 2026-10-15 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open serendipitylabs/dulu-malayalam-asr on Hugging Face](https://huggingface.co/serendipitylabs/dulu-malayalam-asr) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/cde57ebb-917a-4a9c-baf4-a4a12a025505) - [Its page on Mindket](https://mindket.com/p/cde57ebb-917a-4a9c-baf4-a4a12a025505)