coriollon

whisper-large-v3-turbo-russian

README

License: apache-2.0

Headline metrics

General ASR (6 RU test sets, N=500 each, augmented refs):

Table with columns: Metric, Stage AS v2 (prev), Stage AW (this), Δ
Metric	Stage AS v2 (prev)	Stage AW (this)	Δ
WER (aggregate)	9.02 %	9.07 %	+0.05 pp
PER F1 (punct macro F1)	0.398	0.388	−0.010
Cap F1 (word-level case-match)	0.822	0.821	−0.001
Sent F1 (sentence-boundary F1)	0.811	0.818	+0.007

Long-form punct density (150 held-out concat-turns, 12-29 s each):

Table with columns: Metric, Stage AS v2, Stage AW, Δ
Metric	Stage AS v2	Stage AW	Δ
first-half density mean	0.074	0.214	×2.9
second-half density mean	0.090	0.238	×2.7
ratio_med (d2/d1)	1.14	1.00	parity
n_valid (both halves punctuated)	53/150

Per-dataset WER / PER F1

Table with columns: Dataset, AS v2 WER, AW WER, AS v2 PER, AW PER
Dataset	AS v2 WER	AW WER	AS v2 PER	AW PER
Common Voice 21 RU	5.01 %	4.96 %	0.387	0.393
RuLibriSpeech	8.05 %	7.41 %	0.278	0.335
Sberdevices Golos far-field	9.42 %	9.42 %

WER improves on 4/6 datasets; PER regresses on short read-speech (Golos / SOVA) but improves on long meeting-style speech (Podlodka +0.11, RuLibri +0.06) — the corpus AW was tuned for.

What Stage AW fixed

Stage AS v2 was already an accurate Russian punctuator, but on long same-speaker turns (>15 s) the model would front-load punctuation: periods and commas in the first half, then trail off into punctuation-free run-on text. Empirically 65 % of 20-30 s turns in production meeting logs showed this pattern; users saw walls of text that were correct word-for-word but unreadable.

Stage AW retrains on 611 same-speaker concatenated turns (12-29 s each, 3.88 h total) from Pavel's own meeting corpus, with LLM-restored punctuation targets from gemma3:12b. The recipe continues from Stage AS v2 weights (not from Stage AI) so no short-form quality is sacrificed.

Recipe

Init: Stage AS v2 merged weights
Data: 611 rows of same-speaker concat, 12-29 s, gemma3:12b punct-restored targets, WER ≤ 1 % word-preservation verified
LoRA: r=48, target q/k/v/o + fc1/fc2 (same as AS v2)
Schedule: 3 epochs, LR 5e-6 cosine, weight decay 0.01
Compute: ~4 GPU-hours on RTX 4090 mobile

Usage

python

from transformers import WhisperProcessor, WhisperForConditionalGenerationimport torch processor = WhisperProcessor.from_pretrained("coriollon/whisper-large-v3-turbo-russian")model = WhisperForConditionalGeneration.from_pretrained(    "coriollon/whisper-large-v3-turbo-russian",    torch_dtype=torch.float16,).to("cuda") inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")input_features = inputs.input_features.to("cuda", dtype=torch.float16)predicted_ids = model.generate(input_features, language="ru", task="transcribe")transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]

Pre-quantized faster-whisper variants

Table with columns: Folder, Quantization, Size
Folder	Quantization	Size
`ct2_int8_float16/`	int8 weights + fp16 compute	782 MB

python

from huggingface_hub import snapshot_downloadfrom faster_whisper import WhisperModel ct2_path = snapshot_download(    repo_id="coriollon/whisper-large-v3-turbo-russian",    allow_patterns="ct2_int8_float16/*",)model = WhisperModel(f"{ct2_path}/ct2_int8_float16",                    device="cuda", compute_type="int8_float16")segments, _ = model.transcribe("audio.wav", language="ru", beam_size=5)

Reverting to Stage AS v2

The Stage AS v2 revision remains accessible via HF revision pinning:

python

processor = WhisperProcessor.from_pretrained(    "coriollon/whisper-large-v3-turbo-russian",    revision="stage-as-v2",   # git tag pointing to pre-AW commit)

Limitations

On short read-speech (Golos / SOVA) PER F1 drops 0.02-0.11 vs AS v2 because AW was tuned for long conversational turns, not short clean utterances. WER is unaffected.
English-only audio quality inherited from AS v2 baseline — degraded vs vanilla turbo.
Same over-punctuation risk as AS v2 on very short (< 3 s) inputs.

License

Apache 2.0 (inherited from base Whisper model).

Changelog

Stage AW (2026-09-07) — long-form density fine-tune. Continue-train from AS v2 on 611 same-speaker concat-turns (12-29 s, gemma3:12b targets, 3.88 h). Long-form density ×2.7-2.9, n_valid 53→140/150, ratio_med 1.14→1.00. Aggregate WER +0.05 pp (in noise); 4/6 datasets improve.
Metric fix (2026-07-19) — Evaluation harness now counts leading em-dash (Russian dialogue) and standalone ... / … tokens. No change to the released weights, only to how their punctuation quality is reported.
Stage AS v2 (2026-07-14) — LoRA r=48, 3 epochs, rare-mark ×2 sample weighting. WER 9.83 → 8.93 %. PER 0.39 → 0.41, Cap and Sent essentially preserved. Golos WER drops −2 pp on both splits.
Stage AS v1 (2026-07-12) — punctuation & capitalization LoRA fine-tune. Cap F1 0.48 → 0.83, Sent F1 0.45 → 0.81, PER F1 0.20 → 0.39. WER 9.43 → 9.83 %.
Stage AI (previous) — GigaAM-teacher relabel, WER 13.25 → 9.43 %.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

coriollon

Model Tree

Base

openai/whisper-large-v3-turbo

Fine-tuned

this model

Input Modalities

Audio

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Headline metrics

General ASR (6 RU test sets, N=500 each, augmented refs):

Table with columns: Metric, Stage AS v2 (prev), Stage AW (this), Δ
Metric	Stage AS v2 (prev)	Stage AW (this)	Δ
WER (aggregate)	9.02 %	9.07 %	+0.05 pp
PER F1 (punct macro F1)	0.398	0.388	−0.010
Cap F1 (word-level case-match)	0.822	0.821	−0.001
Sent F1 (sentence-boundary F1)	0.811	0.818	+0.007

Long-form punct density (150 held-out concat-turns, 12-29 s each):

Table with columns: Metric, Stage AS v2, Stage AW, Δ
Metric	Stage AS v2	Stage AW	Δ
first-half density mean	0.074	0.214	×2.9
second-half density mean	0.090	0.238	×2.7
ratio_med (d2/d1)	1.14	1.00	parity
n_valid (both halves punctuated)	53/150

Per-dataset WER / PER F1

Table with columns: Dataset, AS v2 WER, AW WER, AS v2 PER, AW PER
Dataset	AS v2 WER	AW WER	AS v2 PER	AW PER
Common Voice 21 RU	5.01 %	4.96 %	0.387	0.393
RuLibriSpeech	8.05 %	7.41 %	0.278	0.335
Sberdevices Golos far-field	9.42 %	9.42 %

WER improves on 4/6 datasets; PER regresses on short read-speech (Golos / SOVA) but improves on long meeting-style speech (Podlodka +0.11, RuLibri +0.06) — the corpus AW was tuned for.

What Stage AW fixed

Recipe

Init: Stage AS v2 merged weights
Data: 611 rows of same-speaker concat, 12-29 s, gemma3:12b punct-restored targets, WER ≤ 1 % word-preservation verified
LoRA: r=48, target q/k/v/o + fc1/fc2 (same as AS v2)
Schedule: 3 epochs, LR 5e-6 cosine, weight decay 0.01
Compute: ~4 GPU-hours on RTX 4090 mobile

Usage

python

from transformers import WhisperProcessor, WhisperForConditionalGenerationimport torch processor = WhisperProcessor.from_pretrained("coriollon/whisper-large-v3-turbo-russian")model = WhisperForConditionalGeneration.from_pretrained(    "coriollon/whisper-large-v3-turbo-russian",    torch_dtype=torch.float16,).to("cuda") inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")input_features = inputs.input_features.to("cuda", dtype=torch.float16)predicted_ids = model.generate(input_features, language="ru", task="transcribe")transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]

Pre-quantized faster-whisper variants

Table with columns: Folder, Quantization, Size
Folder	Quantization	Size
`ct2_int8_float16/`	int8 weights + fp16 compute	782 MB

python

from huggingface_hub import snapshot_downloadfrom faster_whisper import WhisperModel ct2_path = snapshot_download(    repo_id="coriollon/whisper-large-v3-turbo-russian",    allow_patterns="ct2_int8_float16/*",)model = WhisperModel(f"{ct2_path}/ct2_int8_float16",                    device="cuda", compute_type="int8_float16")segments, _ = model.transcribe("audio.wav", language="ru", beam_size=5)

Reverting to Stage AS v2

The Stage AS v2 revision remains accessible via HF revision pinning:

python

processor = WhisperProcessor.from_pretrained(    "coriollon/whisper-large-v3-turbo-russian",    revision="stage-as-v2",   # git tag pointing to pre-AW commit)

Limitations

On short read-speech (Golos / SOVA) PER F1 drops 0.02-0.11 vs AS v2 because AW was tuned for long conversational turns, not short clean utterances. WER is unaffected.
English-only audio quality inherited from AS v2 baseline — degraded vs vanilla turbo.
Same over-punctuation risk as AS v2 on very short (< 3 s) inputs.

License

Apache 2.0 (inherited from base Whisper model).

Changelog

Stage AW (2026-09-07) — long-form density fine-tune. Continue-train from AS v2 on 611 same-speaker concat-turns (12-29 s, gemma3:12b targets, 3.88 h). Long-form density ×2.7-2.9, n_valid 53→140/150, ratio_med 1.14→1.00. Aggregate WER +0.05 pp (in noise); 4/6 datasets improve.
Metric fix (2026-07-19) — Evaluation harness now counts leading em-dash (Russian dialogue) and standalone ... / … tokens. No change to the released weights, only to how their punctuation quality is reported.
Stage AS v2 (2026-07-14) — LoRA r=48, 3 epochs, rare-mark ×2 sample weighting. WER 9.83 → 8.93 %. PER 0.39 → 0.41, Cap and Sent essentially preserved. Golos WER drops −2 pp on both splits.
Stage AS v1 (2026-07-12) — punctuation & capitalization LoRA fine-tune. Cap F1 0.48 → 0.83, Sent F1 0.45 → 0.81, PER F1 0.20 → 0.39. WER 9.43 → 9.83 %.
Stage AI (previous) — GigaAM-teacher relabel, WER 13.25 → 9.43 %.